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

    Neuronpedia

    INDEX
    Explanations

    local

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >';↵
    -0.07
    (drop
    -0.06
    .";
↵
    -0.06
    лює
    -0.06
    _combine
    -0.06
     feed
    -0.06
    Brandon
    -0.06
     Daw
    -0.06
     kindly
    -0.06
    _formula
    -0.06
    POSITIVE LOGITS
     Litecoin
    0.07
    ęp
    0.07
     チ
    0.07
     místní
    0.06
    -aware
    0.06
    GING
    0.06
     RTP
    0.06
     меч
    0.06
    čin
    0.06
    dives
    0.06
    Act Density 0.005%

    No Known Activations