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

    Neuronpedia

    INDEX
    Explanations

    PR

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.08
    行き
    -0.08
    (Search
    -0.07
    תו
    -0.07
    病症
    -0.07
    <ActionResult
    -0.07
    illez
    -0.07
    .Invalid
    -0.07
    ให
    -0.07
    Reflect
    -0.07
    POSITIVE LOGITS
     haired
    0.07
    .getStringExtra
    0.07
    thur
    0.07
    heim
    0.07
     auxiliary
    0.07
    焌
    0.06
     '-')↵
    0.06
    툇
    0.06
    与时
    0.06
     cualquier
    0.06
    Act Density 0.004%

    No Known Activations