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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and variables related to functions and data structures

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

    Variables/indices in code loops

    np_acts-logits-general · gemini-2.0-flash

    variable names followed by indexing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    б
    -0.48
    흡
    -0.40
    ules
    -0.39
     ब
    -0.38
     ب
    -0.36
     Zar
    -0.36
    Zar
    -0.36
     b
    -0.36
     
    -0.35
     nueces
    -0.35
    POSITIVE LOGITS
    GOTREF
    0.91
     betweenstory
    0.90
     objectAtIndex
    0.88
     برانيه
    0.82
     Italijanski
    0.82
    第
    0.81
    batore
    0.80
     ModelExpression
    0.80
    出版年
    0.80
    Vidite
    0.79
    Act Density 1.439%

    No Known Activations