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

    Neuronpedia

    INDEX
    Explanations

    say "("

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itous
    -0.08
     Nina
    -0.08
    dığını
    -0.07
     Davis
    -0.07
    Walker
    -0.07
     Ian
    -0.07
     단
    -0.07
    Davis
    -0.07
    onn
    -0.07
    자를
    -0.07
    POSITIVE LOGITS
    陪
    0.07
    jem
    0.07
     simplement
    0.07
    apgolly
    0.06
    _OPTS
    0.06
     вместе
    0.06
    pon
    0.06
    法治
    0.06
    وج
    0.06
     permutations
    0.06
    Act Density 0.001%

    No Known Activations