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

    Neuronpedia

    INDEX
    Explanations

    sacrifice/purpose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     malfunction
    -0.06
     burden
    -0.06
    '){↵
    -0.06
     cart
    -0.06
    FPS
    -0.06
    Pour
    -0.06
     burdens
    -0.06
     проти
    -0.06
    _photos
    -0.06
    without
    -0.06
    POSITIVE LOGITS
    .train
    0.07
    .threshold
    0.06
     Wrapper
    0.06
     Bro
    0.06
    deen
    0.06
    .gms
    0.06
    anic
    0.06
     Mission
    0.06
    .al
    0.06
     Tile
    0.06
    Act Density 0.045%

    No Known Activations