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

    Neuronpedia

    INDEX
    Explanations

    references to specific film titles or notable media works

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

    versions and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hochspringen
    -0.77
    NameInMap
    -0.70
     Paglinawan
    -0.65
     disambiguazione
    -0.64
     endforeach
    -0.63
    RefNanny
    -0.62
     autorytatywna
    -0.62
     BoxDecoration
    -0.61
    InjectAttribute
    -0.60
    Geplaatst
    -0.59
    POSITIVE LOGITS
    endregion
    0.57
    cyd
    0.47
     QuickBooks
    0.41
    SYNOPSIS
    0.40
    rints
    0.40
    ReLU
    0.38
     рее
    0.36
    illow
    0.35
    enfone
    0.35
     Heraus
    0.34
    Act Density 0.007%

    No Known Activations