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

    Neuronpedia

    INDEX
    Explanations

    non-English languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rampant
    -0.06
    ications
    -0.06
    807
    -0.06
     kappa
    -0.06
    ци
    -0.06
     звіт
    -0.06
     Nie
    -0.06
    545
    -0.06
    417
    -0.06
    icus
    -0.06
    POSITIVE LOGITS
     Please
    0.07
     awarded
    0.07
     kindly
    0.07
    avian
    0.07
    _lock
    0.06
     editor
    0.06
    .Selected
    0.06
     शत
    0.06
    sock
    0.06
     जल
    0.06
    Act Density 0.020%

    No Known Activations