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

    Neuronpedia

    INDEX
    Explanations

    主

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    onia
    -0.07
     titanium
    -0.07
     市
    -0.06
     Increment
    -0.06
     maxValue
    -0.06
     vib
    -0.06
    _Offset
    -0.06
     týden
    -0.06
     recuper
    -0.06
     convolution
    -0.06
    POSITIVE LOGITS
     зам
    0.08
    heritance
    0.07
     א
    0.07
    -root
    0.07
     선수
    0.06
    姆
    0.06
     Holder
    0.06
    حت
    0.06
     evacuate
    0.06
    !"
    0.06
    Act Density 0.002%

    No Known Activations