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

    Neuronpedia

    INDEX
    Explanations

    percentage and format-related syntax characters

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

    user/%user/contact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.58
     India
    -0.48
     Corea
    -0.48
     Brasilien
    -0.45
    illow
    -0.44
     Asien
    -0.44
     Suecia
    -0.43
    India
    -0.43
    Draw
    -0.43
    化
    -0.42
    POSITIVE LOGITS
    /%
    1.59
    =%
    1.55
     (%
    1.32
    (%
    1.32
    :%
    1.28
    _%
    1.21
    -%
    1.21
    ,%
    1.20
    ("%
    1.10
    [%
    1.09
    Act Density 0.010%

    No Known Activations