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

    Neuronpedia

    INDEX
    Explanations

    Random Topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inden
    -0.08
    afia
    -0.08
    潜艇
    -0.08
    inan
    -0.07
    gage
    -0.07
    .Home
    -0.07
     מהמ
    -0.07
    ":"+
    -0.07
     yapılacak
    -0.07
    冏
    -0.07
    POSITIVE LOGITS
     broadcaster
    0.06
    自治区
    0.06
     enterprises
    0.06
     terminator
    0.06
     politics
    0.06
    Guy
    0.06
     recognized
    0.06
    维奇
    0.06
     scare
    0.06
    Scalar
    0.06
    Act Density 0.206%

    No Known Activations