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

    Neuronpedia

    INDEX
    Explanations

    Technical/informational writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ului
    -0.07
     Müş
    -0.07
    abama
    -0.06
    built
    -0.06
    jícím
    -0.06
    voucher
    -0.06
    ória
    -0.06
     ako
    -0.06
    Behaviour
    -0.06
    bred
    -0.06
    POSITIVE LOGITS
    (pattern
    0.07
    ony
    0.06
    はい
    0.06
    亿
    0.06
    mix
    0.06
    .partition
    0.06
    essenger
    0.06
     stay
    0.06
    (Text
    0.06
    );;↵
    0.06
    Act Density 0.000%

    No Known Activations