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

    Neuronpedia

    INDEX
    Explanations

    alternatives and questions related to choices or decisions

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

    or questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InputBorder
    -0.55
     Signalez
    -0.53
     Infórmanos
    -0.52
    esgue
    -0.46
    ScopeManager
    -0.43
    DebuggerNonUser
    -0.43
     guan
    -0.41
    conio
    -0.41
    杵
    -0.40
     ux
    -0.40
    POSITIVE LOGITS
     justru
    0.80
     sesuatu
    0.66
    それとも
    0.65
     yoksa
    0.62
     préfé
    0.62
     malah
    0.59
     dopiero
    0.59
     something
    0.58
     is
    0.58
     jedynie
    0.57
    Act Density 0.030%

    No Known Activations