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

    Neuronpedia

    INDEX
    Explanations

    actions and processes related to inquiry and evaluation

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

    contextual phrase following certain actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.49
    :
    -0.41
     Pav
    -0.37
    <eos>
    -0.36
     pav
    -0.35
    ;
    -0.35
     due
    -0.35
     fut
    -0.35
    4
    -0.34
    2
    -0.34
    POSITIVE LOGITS
     linkovi
    0.76
     estekak
    0.69
     Wicidata
    0.69
    Personendaten
    0.67
     Photocase
    0.66
     ModelExpression
    0.64
     beſch
    0.64
     queſta
    0.64
     للاسماء
    0.63
    tagHelperRunner
    0.62
    Act Density 0.065%

    No Known Activations