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

    Neuronpedia

    INDEX
    Explanations

    offer officially

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UNIVERSITY
    0.45
     vgl
    0.44
    蓍
    0.44
    한편
    0.43
    輝
    0.43
    ন্যা
    0.42
    relli
    0.42
    писки
    0.41
    炽
    0.41
     bibliography
    0.41
    POSITIVE LOGITS
     afresh
    0.42
     ozone
    0.41
    เล่น
    0.40
    based
    0.40
    polyfill
    0.40
    global
    0.39
     based
    0.39
    soul
    0.39
     可愛
    0.39
     labile
    0.39
    Act Density 0.000%

    No Known Activations