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

    Neuronpedia

    INDEX
    Explanations

    programming and general text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     беременности
    -0.07
    bil
    -0.06
    帯
    -0.06
    也有
    -0.06
    ูงส
    -0.06
     บาง
    -0.06
     Tonight
    -0.06
    бач
    -0.06
     osob
    -0.06
    ocup
    -0.06
    POSITIVE LOGITS
    .Guid
    0.07
     inaugural
    0.06
     typed
    0.06
     permanent
    0.06
    โน
    0.06
     　
    0.06
     REPL
    0.06
     oldukça
    0.06
     vim
    0.06
    İN
    0.06
    Act Density 0.000%

    No Known Activations