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

    Neuronpedia

    INDEX
    Explanations

    Nonsensical character combinations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sixth
    -0.07
    _wallet
    -0.07
     footprint
    -0.07
     fantas
    -0.07
     infants
    -0.07
     ал
    -0.07
    ByteBuffer
    -0.07
     (!((
    -0.07
    arte
    -0.07
     اساس
    -0.06
    POSITIVE LOGITS
     Neue
    0.07
     دسته
    0.07
    Copy
    0.06
    ucch
    0.06
     TableName
    0.06
    ｍ
    0.06
    /column
    0.06
     absorbing
    0.06
     points
    0.06
    date
    0.06
    Act Density 0.017%

    No Known Activations