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

    Neuronpedia

    INDEX
    Explanations

    send

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    istani
    -0.08
    贫穷
    -0.07
    DAQ
    -0.07
     attorneys
    -0.07
    oto
    -0.07
    邮轮
    -0.07
    同胞
    -0.07
     Corm
    -0.06
    נית
    -0.06
    口径
    -0.06
    POSITIVE LOGITS
    ,msg
    0.09
    保持着
    0.07
     quel
    0.07
    aways
    0.07
     específ
    0.07
     Ré
    0.07
    ków
    0.07
    半个月
    0.07
    �
    0.07
    _bp
    0.07
    Act Density 0.120%

    No Known Activations