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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    direction
    -0.07
    ('(
    -0.07
    Ci
    -0.06
    -awesome
    -0.06
    ="__
    -0.06
    hos
    -0.06
    script
    -0.06
    imu
    -0.06
    maker
    -0.06
    .ReadFile
    -0.06
    POSITIVE LOGITS
     backstage
    0.06
     Clerk
    0.06
     Gear
    0.06
    �
    0.06
     служби
    0.06
    leyin
    0.06
    ают
    0.06
     Česká
    0.06
    OUN
    0.06
     حسب
    0.06
    Act Density 0.155%

    No Known Activations