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

    Neuronpedia

    INDEX
    Explanations

    Go import statements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _atoms
    -0.07
     assisted
    -0.07
     acquiring
    -0.07
    Repeat
    -0.07
    пре
    -0.07
    _adapter
    -0.07
     engineer
    -0.07
    彦
    -0.06
     Initially
    -0.06
    反击
    -0.06
    POSITIVE LOGITS
    满意度
    0.09
     cresc
    0.08
    有意思
    0.07
     sidel
    0.07
    脱颖
    0.07
     раздел
    0.07
    uestos
    0.06
     makers
    0.06
     cityName
    0.06
    生育
    0.06
    Act Density 0.003%

    No Known Activations