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

    Neuronpedia

    INDEX
    Explanations

    say "to"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sund
    -0.07
    (n
    -0.07
     budeme
    -0.07
    .word
    -0.06
     n
    -0.06
     prolifer
    -0.06
     bush
    -0.06
     kone
    -0.06
    ryptography
    -0.06
    esco
    -0.06
    POSITIVE LOGITS
    커스
    0.07
    pc
    0.06
    찬
    0.06
    青
    0.06
    Mods
    0.06
    _using
    0.06
    _COMPANY
    0.06
     Using
    0.06
     newly
    0.06
    911
    0.06
    Act Density 0.135%

    No Known Activations