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

    Neuronpedia

    INDEX
    Explanations

    code and technical discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Logged
    -0.07
     Legend
    -0.07
    _posts
    -0.07
    圣
    -0.06
    склад
    -0.06
     Stroke
    -0.06
    .yaml
    -0.06
    ห
    -0.06
     Наз
    -0.06
    .decrypt
    -0.06
    POSITIVE LOGITS
    (minutes
    0.06
     criminal
    0.06
    .
    0.06
     reveals
    0.06
    ....↵↵
    0.06
     emoc
    0.06
    _marks
    0.06
     Exp
    0.06
     kön
    0.06
    ji
    0.06
    Act Density 0.000%

    No Known Activations