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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ชาต
    -0.07
     Jiří
    -0.07
     авг
    -0.07
     Krishna
    -0.07
     NSA
    -0.06
     Н
    -0.06
    _traits
    -0.06
     downfall
    -0.06
     Доб
    -0.06
     anatom
    -0.06
    POSITIVE LOGITS
    (dt
    0.07
     simpler
    0.06
    -columns
    0.06
    عم
    0.06
    �
    0.06
    compare
    0.06
     paraph
    0.06
    velope
    0.06
    overall
    0.06
    อนไลน
    0.06
    Act Density 0.000%

    No Known Activations