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

    Neuronpedia

    INDEX
    Explanations

    expressions of curiosity and desire for interaction or feedback

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

    "love to" or "like to"

    np_acts-logits-general · gemini-2.0-flash

    love to hear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transfieras
    -0.79
    IUrlHelper
    -0.73
    UnknownFieldSet
    -0.68
     MainAxisSize
    -0.67
    openConnection
    -0.66
     MotionEvent
    -0.65
    ComponentName
    -0.63
    LookAnd
    -0.61
    éroport
    -0.60
    السكان
    -0.59
    POSITIVE LOGITS
     hearing
    0.83
     seeing
    0.72
     gärna
    0.68
     if
    0.66
    hearing
    0.62
     hear
    0.61
     knowing
    0.59
     see
    0.58
    Hearing
    0.58
     mendengar
    0.58
    Act Density 0.106%

    No Known Activations