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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    こと
    -0.07
    gem
    -0.07
    omen
    -0.07
     etme
    -0.07
     Paran
    -0.07
     yere
    -0.07
     differs
    -0.07
    aliz
    -0.07
    ih
    -0.07
    эн
    -0.07
    POSITIVE LOGITS
    χρι
    0.07
    hawk
    0.06
    аток
    0.06
    _SK
    0.06
    .sup
    0.06
    ыџN
    0.06
     Greeks
    0.06
    Extended
    0.06
     ambit
    0.06
    (baseUrl
    0.06
    Act Density 0.020%

    No Known Activations