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

    Neuronpedia

    INDEX
    Explanations

    abrupt halt, avoid rushing, caused chaos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    方的
    0.46
     poucos
    0.46
    系列的
    0.46
    且
    0.46
    সাথে
    0.45
     XLSX
    0.45
    移除
    0.44
    找
    0.44
    وب
    0.44
    ن
    0.43
    POSITIVE LOGITS
     tulis
    0.44
     ак
    0.44
     す
    0.43
     boil
    0.42
     acumen
    0.41
     വരു
    0.40
     הח
    0.40
     jų
    0.40
    maur
    0.39
    pak
    0.39
    Act Density 0.001%

    No Known Activations