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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values or integer variables

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

    n assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -1.30
    <unused41>
    -0.96
    <unused28>
    -0.96
    <unused8>
    -0.96
    <unused52>
    -0.96
    <unused79>
    -0.96
    <unused43>
    -0.96
    <unused74>
    -0.96
    <unused42>
    -0.96
    <unused14>
    -0.96
    POSITIVE LOGITS
    Herkunft
    0.28
     concreto
    0.26
     requerido
    0.26
     n
    0.25
     Tecnología
    0.25
     plancher
    0.25
     langage
    0.24
     ingres
    0.23
     plateado
    0.23
     Suiza
    0.23
    Act Density 0.022%

    No Known Activations