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

    Neuronpedia

    INDEX
    Explanations

    references to decision-making processes

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

    decisions or conditions

    np_acts-logits-general · gemini-2.0-flash

    making a decision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    componentDid
    -0.46
    hideLoading
    -0.44
    ionView
    -0.44
    QueryParam
    -0.42
     CWE
    -0.42
    ftc
    -0.42
    igens
    -0.42
    OOTDTY
    -0.42
    imerick
    -0.41
     AssemblyTitle
    -0.41
    POSITIVE LOGITS
     decided
    2.15
     decision
    2.01
     decide
    1.99
    decided
    1.91
     Decided
    1.86
     decides
    1.84
    decide
    1.80
    decision
    1.77
     Decide
    1.76
     décidé
    1.75
    Act Density 0.303%

    No Known Activations