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

    Neuronpedia

    INDEX
    Explanations

    have no

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вест
    0.33
    ляти
    0.32
    संहार
    0.32
    濁
    0.32
    лями
    0.31
    肃
    0.31
     ضرور
    0.30
    рья
    0.30
    哌
    0.30
     ఏద
    0.29
    POSITIVE LOGITS
     no
    4.06
    no
    3.14
     No
    2.91
    No
    2.91
     NO
    2.58
     keine
    2.48
    ไม่มี
    2.38
    NO
    2.16
     kein
    2.14
     geen
    2.09
    Act Density 0.386%

    No Known Activations