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

    Neuronpedia

    INDEX
    Explanations

    managed care

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🎿
    -0.08
     ((((
    -0.07
    quí
    -0.07
    ᅧ
    -0.07
     Missile
    -0.07
     Shard
    -0.07
    顺利
    -0.06
    (elm
    -0.06
    られて
    -0.06
    递
    -0.06
    POSITIVE LOGITS
    Scaler
    0.07
    是一家
    0.07
    multi
    0.07
    oni
    0.07
    Func
    0.07
     popcorn
    0.07
     Lang
    0.07
    _params
    0.07
    小伙伴
    0.07
    �
    0.07
    Act Density 0.158%

    No Known Activations