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

    Neuronpedia

    INDEX
    Explanations

    action-oriented words related to execution and fulfillment of plans or agreements

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

    implementing or enforcing actions

    np_acts-logits-general · gemini-2.0-flash

    executing or performing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hassee
    -0.47
    setcounter
    -0.43
     gemacht
    -0.43
     исто
    -0.42
     alles
    -0.42
     Alles
    -0.41
     attention
    -0.41
     indulgence
    -0.41
    とこ
    -0.40
     않
    -0.40
    POSITIVE LOGITS
    ScopeManager
    0.84
    </tfoot>
    0.79
     promised
    0.76
    WindowConstants
    0.72
    oneofs
    0.71
    Tarifs
    0.68
    invokeLater
    0.67
    +:+
    0.67
    GraphicsUnit
    0.65
     promises
    0.65
    Act Density 0.264%

    No Known Activations