Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    actions and transformations related to progression, taking steps, and changes in state or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows certain verbs (take, raise)

    np_acts-logits-general · gemini-2.0-flash

    take action, go further

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Económica
    -0.66
     Tampoco
    -0.64
    IntoConstraints
    -0.61
     noDo
    -0.61
     htons
    -0.60
     Hift
    -0.56
     fubject
    -0.55
     ervoor
    -0.54
     års
    -0.53
    urlpatterns
    -0.53
    POSITIVE LOGITS
     ddelweddau
    0.60
     transcends
    0.59
     متعلقه
    0.56
    一歩
    0.56
     intensify
    0.55
     autorytatywna
    0.55
     extrapolation
    0.54
     intensified
    0.54
    更に
    0.54
     refinement
    0.54
    Act Density 0.132%

    No Known Activations