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

    Neuronpedia

    INDEX
    Explanations

    Egypt

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vention
    -0.07
     brides
    -0.07
     perf
    -0.06
    .Put
    -0.06
    Soon
    -0.06
    ød
    -0.06
    那种
    -0.06
    Guy
    -0.06
    struments
    -0.06
    Putting
    -0.06
    POSITIVE LOGITS
    (`${
    0.08
    �
    0.07
    ?>">↵
    0.07
    ２０
    0.06
    _rep
    0.06
     mutually
    0.06
     Jarvis
    0.06
    ственная
    0.06
     protesting
    0.06
     fila
    0.06
    Act Density 0.030%

    No Known Activations