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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     everything
    -0.08
    yl
    -0.07
     TypeName
    -0.07
    da
    -0.07
     hell
    -0.07
    mall
    -0.07
     Most
    -0.07
     criteria
    -0.07
     TERM
    -0.07
    塔
    -0.06
    POSITIVE LOGITS
     flips
    0.07
    Walk
    0.07
     Phot
    0.07
    โชค
    0.06
    ﺝ
    0.06
     пользоват
    0.06
     víct
    0.06
    �
    0.06
    (dis
    0.06
    Глав
    0.06
    Act Density 0.000%

    No Known Activations