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

    Neuronpedia

    INDEX
    Explanations

    dangerous

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    స్
    1.30
    s
    1.16
    ある
    1.12
    یشہ
    1.08
    ensioni
    1.06
    ripcion
    1.05
    o
    1.03
    e
    1.02
    𝗲
    1.01
    ኺ
    0.98
    POSITIVE LOGITS
    ↵
    1.26
     Doesn
    0.93
    ש
    0.92
     πρέπει
    0.91
    ลำ
    0.91
     defies
    0.88
     doesn
    0.88
     梅
    0.86
     hasn
    0.82
     Dabei
    0.81
    Act Density 0.444%

    No Known Activations