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

    Neuronpedia

    INDEX
    Explanations

    DanielobtainedearningwidgetsMonitoring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    我們的
    0.49
    下标
    0.47
    ទឹក
    0.46
    0.45
    ﻠ
    0.44
    0.44
    名称
    0.44
    㫧
    0.44
    ونَ
    0.43
     हमारे
    0.43
    POSITIVE LOGITS
     spline
    0.46
    :
    0.42
     CLARK
    0.42
     distinguished
    0.41
     सांगित
    0.41
     transgenic
    0.41
     SEAL
    0.40
     Fian
    0.40
    cami
    0.40
     Larry
    0.39
    Act Density 0.003%

    No Known Activations