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

    Neuronpedia

    INDEX
    Explanations

    jury

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fat
    -0.07
    ncoder
    -0.07
     letech
    -0.07
    Celebr
    -0.06
     Gram
    -0.06
     mio
    -0.06
     Сам
    -0.06
    Release
    -0.06
    icare
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     dung
    0.06
     Ek
    0.06
    μα
    0.06
    .cos
    0.06
     duy
    0.06
     vorhand
    0.06
     unreasonable
    0.06
    $',
    0.06
     повер
    0.06
    ination
    0.06
    Act Density 0.003%

    No Known Activations