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

    Neuronpedia

    INDEX
    Explanations

    coding syntax and type declarations

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

    programming data types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     recuperación
    -0.31
    ush
    -0.28
    keeps
    -0.27
     ведет
    -0.27
    ّد
    -0.27
    ity
    -0.26
     rodea
    -0.26
     ün
    -0.26
    รม
    -0.26
     conséquence
    -0.25
    POSITIVE LOGITS
    exitRule
    0.70
     BoxFit
    0.69
    0.68
    tagext
    0.66
    vician
    0.65
    principalTable
    0.64
    IVEREF
    0.63
     الرياضيه
    0.60
     مرئيه
    0.60
    posedge
    0.60
    Act Density 0.053%

    No Known Activations