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

    Neuronpedia

    INDEX
    Explanations

    actions related to taking or making decisions

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

    "take" followed by a preposition or noun

    np_acts-logits-general · gemini-2.0-flash

    taking action or initiative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    riwal
    -0.76
    ########.
    -0.70
    __':
    -0.69
    __":
    -0.65
    VersionUID
    -0.65
     StatelessWidget
    -0.64
    Enllaces
    -0.63
    decision
    -0.60
     незавершена
    -0.59
     StatefulWidget
    -0.58
    POSITIVE LOGITS
     stock
    0.64
     steps
    0.59
     baby
    0.56
    iedenen
    0.55
     calculated
    0.53
     proactive
    0.53
     neceffary
    0.51
     peł
    0.50
     concrete
    0.50
     pragmatic
    0.50
    Act Density 0.132%

    No Known Activations