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

    Neuronpedia

    INDEX
    Explanations

    Civil

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pins
    -0.07
     "\↵
    -0.07
     MPS
    -0.07
     MIS
    -0.07
     QUESTION
    -0.07
     Institute
    -0.07
     scipy
    -0.06
    cedes
    -0.06
    💃
    -0.06
     לראש
    -0.06
    POSITIVE LOGITS
    鸮
    0.08
    亲
    0.07
    -sort
    0.07
    捞
    0.07
    쪗
    0.07
     dabei
    0.07
    _highlight
    0.07
    iversal
    0.07
     بعد
    0.07
    问题
    0.07
    Act Density 0.002%

    No Known Activations