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

    Neuronpedia

    INDEX
    Explanations

    quantitative measures or values related to performance or metrics

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

    API request fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    umumkan
    -0.37
     pertanian
    -0.37
     obč
    -0.37
     extensão
    -0.36
     terbesar
    -0.35
     ciudadanía
    -0.35
     cokelat
    -0.35
     próxima
    -0.34
     kebenaran
    -0.34
     posibilidad
    -0.34
    POSITIVE LOGITS
    tvguidetime
    0.60
    SequentialGroup
    0.57
     resourceCulture
    0.57
    +#+#
    0.56
    Ằ
    0.55
     pinulongan
    0.54
     Meksiku
    0.54
    はじめに
    0.53
    awtextra
    0.52
    انيف
    0.51
    Act Density 0.047%

    No Known Activations