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

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    杓
    -0.08
    砵
    -0.07
     ag
    -0.07
     erre
    -0.07
     In
    -0.07
     пл
    -0.07
    混合
    -0.06
     invalidate
    -0.06
     chalk
    -0.06
    )object
    -0.06
    POSITIVE LOGITS
    ক
    0.07
     rookies
    0.07
    옮
    0.07
    CDF
    0.07
    出自
    0.07
    _MEMBERS
    0.07
     �
    0.07
    sf
    0.07
     encode
    0.06
    LIKE
    0.06
    Act Density 0.032%

    No Known Activations