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

    Neuronpedia

    INDEX
    Explanations

    hyphenated phrases or words

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

    Text followed by a hyphen

    np_acts-logits-general · gemini-2.0-flash

    technical error codes or notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.74
    TagMode
    -0.69
    PutMapping
    -0.64
    ’
    -0.63
    ンドウ
    -0.62
    Hic
    -0.60
    Rij
    -0.60
    ائج
    -0.59
    жки
    -0.58
    itect
    -0.58
    POSITIVE LOGITS
    ----------------
    1.28
    awtextra
    1.27
     -
    1.16
    Capítulo
    1.13
    ---------------
    1.11
    ">-
    1.07
    {-
    1.00
    &-
    1.00
     disambiguazione
    0.97
     -"
    0.96
    Act Density 0.346%

    No Known Activations