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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    官方
    -0.08
    VIN
    -0.07
     copp
    -0.07
     mos
    -0.07
    Counts
    -0.07
     announcing
    -0.07
    蒙
    -0.06
    маз
    -0.06
     barrel
    -0.06
    Merchant
    -0.06
    POSITIVE LOGITS
    させ
    0.06
    paste
    0.06
     suspicion
    0.06
    ели
    0.06
     spine
    0.06
    εχ
    0.05
    _lock
    0.05
    发送
    0.05
     být
    0.05
     observes
    0.05
    Act Density 0.155%

    No Known Activations