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

    Neuronpedia

    INDEX
    Explanations

    key verbs and actions that indicate processes or events

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

    actions completed previously

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ciepła
    -0.30
     drogi
    -0.29
     bakım
    -0.29
     kapturem
    -0.29
     Commencez
    -0.28
     jsPsych
    -0.27
     silvestre
    -0.27
    pushFollow
    -0.27
     Schicht
    -0.27
    crites
    -0.27
    POSITIVE LOGITS
     previously
    0.63
    Previously
    0.63
     Previously
    0.61
     already
    0.60
     anteriormente
    0.58
     ALREADY
    0.58
    already
    0.57
     Already
    0.57
     Exacts
    0.57
    previously
    0.57
    Act Density 0.424%

    No Known Activations