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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     mě
    -0.07
     Cous
    -0.06
    ρά
    -0.06
    hil
    -0.06
    (`<
    -0.06
     carve
    -0.06
    ตาม
    -0.06
     tongue
    -0.06
    [thread
    -0.06
    POSITIVE LOGITS
    release
    0.07
     خطر
    0.07
     Vegas
    0.06
     sexism
    0.06
    acf
    0.06
    ‍
    0.06
     (!_
    0.06
    sentence
    0.06
    활동
    0.06
     администра
    0.06
    Act Density 0.000%

    No Known Activations