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

    Neuronpedia

    INDEX
    Explanations

    references to ease of use or accessibility in various contexts

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

    Describes something easily done or obtained

    np_acts-logits-general · gemini-2.0-flash

    easily accessible and controllable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aveug
    -0.57
    expert
    -0.55
     Specialized
    -0.55
    especial
    -0.54
     avancé
    -0.54
     sélectionnés
    -0.53
     postIndex
    -0.53
     autorizado
    -0.53
     Expert
    -0.53
    incorrect
    -0.52
    POSITIVE LOGITS
     accessible
    1.26
     قابل
    1.25
     easily
    1.19
    可
    1.14
     controllable
    1.10
     reachable
    1.09
     amenable
    1.06
     manageable
    1.06
     detectable
    1.06
     readable
    1.04
    Act Density 0.445%

    No Known Activations