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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dostup
    -0.07
    札
    -0.06
    _erase
    -0.06
    사회
    -0.06
    administration
    -0.06
    密码
    -0.06
    _PROPERTIES
    -0.06
    adapt
    -0.06
    -community
    -0.06
    lets
    -0.06
    POSITIVE LOGITS
    ={({
    0.07
    Outer
    0.07
     Canucks
    0.06
     Burb
    0.06
     Scatter
    0.06
    licity
    0.06
     آذرب
    0.06
     vows
    0.06
     distur
    0.06
     Outer
    0.06
    Act Density 0.071%

    No Known Activations