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

    Neuronpedia

    INDEX
    Explanations

    HTML attribute assignments

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

    HTML form options and modules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }),
    -0.30
     physically
    -0.28
     Brod
    -0.28
     –
    -0.26
    除了
    -0.25
    —
    -0.25
     Beyond
    -0.24
     enemmän
    -0.24
     enough
    -0.24
    tgz
    -0.24
    POSITIVE LOGITS
     autorytatywna
    0.85
    ValueStyle
    0.83
     مرئيه
    0.76
     gynhyrchwyd
    0.75
    :✨
    0.74
    IntoConstraints
    0.73
    InputBorder
    0.72
     nakalista
    0.70
     $_"
    0.70
     disambiguazione
    0.69
    Act Density 0.006%

    No Known Activations