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

    Neuronpedia

    INDEX
    Explanations

    commons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.41
    ע
    1.30
    1
    1.29
    al
    1.28
    were
    1.27
    ty
    1.26
    they
    1.23
    ت
    1.22
    an
    1.18
    the
    1.18
    POSITIVE LOGITS
    PlayerDataCache
    1.16
     Commons
    1.04
    ሳሪያ
    1.04
     tượng
    0.98
    ަތ
    0.96
    يل
    0.96
     harán
    0.95
    簱
    0.95
    ח
    0.95
     commons
    0.94
    Act Density 0.001%

    No Known Activations