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

    Neuronpedia

    INDEX
    Explanations

    themes related to personal convictions, principles, and integrity

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

    values, principles, convictions, ideals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     imageNamed
    -0.42
     contextLoads
    -0.38
     pranks
    -0.36
     ExecuteAsync
    -0.35
    ElementException
    -0.34
    getahuan
    -0.34
    utta
    -0.33
    itism
    -0.33
    ParseTree
    -0.33
    estimm
    -0.32
    POSITIVE LOGITS
    SequentialGroup
    0.50
     nahilalakip
    0.47
    tvguidetime
    0.46
     الحره
    0.46
    IntoConstraints
    0.45
     становника
    0.44
     Valores
    0.44
    WarningLevel
    0.44
     values
    0.44
     convictions
    0.43
    Act Density 0.233%

    No Known Activations