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

    Neuronpedia

    INDEX
    Explanations

    say "s" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sails
    -0.08
    Scanner
    -0.07
    history
    -0.07
     Harbor
    -0.07
     Iter
    -0.07
    Uint
    -0.07
     Ryder
    -0.06
    .history
    -0.06
    上百
    -0.06
    ReactDOM
    -0.06
    POSITIVE LOGITS
    .Part
    0.08
    ces
    0.08
    收費
    0.08
    日讯
    0.07
    Offsets
    0.07
     yuan
    0.07
     relação
    0.07
     czas
    0.07
     су
    0.07
    \xd
    0.07
    Act Density 0.032%

    No Known Activations