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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -night
    -0.07
    thers
    -0.07
     withd
    -0.06
     husband
    -0.06
    _delay
    -0.06
     loaf
    -0.06
    _placeholder
    -0.06
    client
    -0.06
     blo
    -0.06
     naar
    -0.06
    POSITIVE LOGITS
     говор
    0.07
     Cornell
    0.07
    @Enable
    0.07
    Applied
    0.07
    Science
    0.07
     kinds
    0.06
     Kitt
    0.06
    .Points
    0.06
    probably
    0.06
     prospective
    0.06
    Act Density 0.030%

    No Known Activations