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

    Neuronpedia

    INDEX
    Explanations

    Formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _bank
    -0.08
    neider
    -0.07
    アン
    -0.07
    lse
    -0.07
    -'+
    -0.07
     miscellaneous
    -0.07
    ्स
    -0.06
    αρά
    -0.06
    .Must
    -0.06
     huy
    -0.06
    POSITIVE LOGITS
     perché
    0.07
     because
    0.07
    стві
    0.07
     shuffled
    0.06
     Because
    0.06
     dvěma
    0.06
     Utf
    0.06
    .site
    0.06
    because
    0.06
     weil
    0.06
    Act Density 0.058%

    No Known Activations