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

    Neuronpedia

    INDEX
    Explanations

    colons/equals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ans
    -0.07
    smarty
    -0.06
     ways
    -0.06
     Clemson
    -0.06
    ψ
    -0.06
    ATH
    -0.06
    خیص
    -0.06
     ב
    -0.06
    باش
    -0.06
    ":@"
    -0.06
    POSITIVE LOGITS
    .models
    0.07
    deserialize
    0.07
    terní
    0.07
    '/
    0.07
    onic
    0.07
    'gc
    0.07
    führt
    0.06
     renovation
    0.06
    dpi
    0.06
           
    0.06
    Act Density 0.042%

    No Known Activations