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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    男孩
    -0.07
     Setter
    -0.07
     buy
    -0.07
    刚刚
    -0.07
    (Long
    -0.07
    具体
    -0.07
    只剩
    -0.07
     still
    -0.07
    Captain
    -0.07
     Facing
    -0.07
    POSITIVE LOGITS
    羱
    0.08
    อำ
    0.08
    ᗯ
    0.07
    ᕤ
    0.07
     đẩ
    0.07
    𬍤
    0.07
    taboola
    0.07
    errupt
    0.07
    _Widget
    0.07
    滦
    0.07
    Act Density 0.000%

    No Known Activations