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

    Neuronpedia

    INDEX
    Explanations

    Enron emails

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aph
    -0.07
    ikon
    -0.07
     Mac
    -0.07
    ustr
    -0.07
    ені
    -0.06
    NULL
    -0.06
    SK
    -0.06
     gastr
    -0.06
    Seven
    -0.06
    ’h
    -0.06
    POSITIVE LOGITS
     fuss
    0.07
     spolu
    0.07
     فتح
    0.07
     /^[
    0.06
     नर
    0.06
    stem
    0.06
    nic
    0.06
     clic
    0.06
    LANGUAGE
    0.06
    _standard
    0.06
    Act Density 0.007%

    No Known Activations