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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     algumas
    -0.06
     elast
    -0.06
     لإ
    -0.06
    ूत
    -0.06
     ImportError
    -0.06
    岗位
    -0.06
     фактор
    -0.06
     OE
    -0.06
    vocab
    -0.06
     iq
    -0.06
    POSITIVE LOGITS
    Get
    0.07
    ventions
    0.07
    _vals
    0.07
    ifest
    0.07
     financially
    0.07
     durations
    0.07
    Information
    0.07
     agreement
    0.07
     करत
    0.06
    аза
    0.06
    Act Density 0.002%

    No Known Activations