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

    Neuronpedia

    INDEX
    Explanations

    reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    loub
    -0.07
     ifdef
    -0.06
     ayar
    -0.06
    .mc
    -0.06
     поверх
    -0.06
    <Model
    -0.06
     Kingdom
    -0.06
     RM
    -0.06
     Moor
    -0.06
    (iv
    -0.06
    POSITIVE LOGITS
    뉴
    0.06
    expires
    0.06
     �
    0.06
    prises
    0.06
     lifes
    0.06
    .data
    0.06
    ions
    0.06
    disk
    0.06
    ूरत
    0.06
    _mm
    0.06
    Act Density 0.002%

    No Known Activations