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

    Neuronpedia

    INDEX
    Explanations

    actions and processes related to completing or modifying tasks

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

    completed actions and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onwards
    -0.45
    aronder
    -0.39
     continually
    -0.38
    WebControls
    -0.38
     forthcoming
    -0.36
     ویکی‌پدیای
    -0.36
     erhält
    -0.36
     actualidad
    -0.35
     readily
    -0.35
     kini
    -0.35
    POSITIVE LOGITS
     blew
    0.63
    happened
    0.59
    burned
    0.58
    did
    0.57
     flipped
    0.57
     originalmente
    0.56
     modeled
    0.55
    wrote
    0.55
     smelled
    0.55
     burned
    0.53
    Act Density 0.165%

    No Known Activations