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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    㮾
    -0.07
     sø
    -0.07
     ballistic
    -0.07
     Gold
    -0.07
    ampoline
    -0.07
     agricultural
    -0.07
    ından
    -0.07
     trợ
    -0.07
     savings
    -0.07
     azt
    -0.07
    POSITIVE LOGITS
    implements
    0.08
     register
    0.07
    通知
    0.07
    Charge
    0.06
     removing
    0.06
    去了
    0.06
    抄
    0.06
     STRUCT
    0.06
    自己
    0.06
    ancies
    0.06
    Act Density 0.062%

    No Known Activations