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

    Neuronpedia

    INDEX
    Explanations

    quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /
    -0.07
    .,
    -0.06
    .validator
    -0.06
    .so
    -0.06
    onces
    -0.06
    307
    -0.06
    raž
    -0.06
    .codec
    -0.06
     reck
    -0.06
     then
    -0.06
    POSITIVE LOGITS
    inyin
    0.08
    quee
    0.07
    ull
    0.07
    hled
    0.07
    _DIRECTORY
    0.07
    θμ
    0.06
     }
↵
↵
↵
↵
    0.06
     Fireplace
    0.06
     درس
    0.06
    AndFeel
    0.06
    Act Density 0.152%

    No Known Activations