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

    Neuronpedia

    INDEX
    Explanations

    academic concept

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    бі
    0.65
    రోజు
    0.62
    dracht
    0.61
    Бі
    0.61
     नींव
    0.60
    电设备
    0.59
    isième
    0.59
     efflux
    0.59
    厚生
    0.59
     périphérique
    0.59
    POSITIVE LOGITS
     without
    0.56
     Knee
    0.53
     Interference
    0.53
     Änderungen
    0.52
     kg
    0.51
     ko
    0.51
     بدون
    0.51
    ง่าย
    0.51
     ohne
    0.50
     coarse
    0.50
    Act Density 0.000%

    No Known Activations