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

    Neuronpedia

    INDEX
    Explanations

    f

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     guesses
    -0.07
    _element
    -0.06
    365
    -0.06
    /chat
    -0.06
     integers
    -0.06
    Sink
    -0.06
    ，
    -0.06
     kutje
    -0.06
    šť
    -0.06
    znik
    -0.06
    POSITIVE LOGITS
     perg
    0.06
     Alien
    0.06
    ")->
    0.06
     Quando
    0.06
     banning
    0.06
    -q
    0.06
    .Secret
    0.06
    ерату
    0.06
    .mi
    0.06
     цар
    0.06
    Act Density 0.013%

    No Known Activations