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

    Neuronpedia

    INDEX
    Explanations

    handled

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     getColumn
    -0.07
    atem
    -0.07
    quant
    -0.07
    UTE
    -0.07
     mắc
    -0.07
    .Publish
    -0.07
     Adolf
    -0.06
    �
    -0.06
     Entrepreneur
    -0.06
    学会
    -0.06
    POSITIVE LOGITS
    _hash
    0.07
     overlap
    0.07
    묾
    0.07
     Seam
    0.07
     Spice
    0.06
    sanitize
    0.06
    出厂
    0.06
    warf
    0.06
    チーム
    0.06
     iç
    0.06
    Act Density 0.001%

    No Known Activations