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

    Neuronpedia

    INDEX
    Explanations

    you are a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    й
    0.95
     glab
    0.93
     antennes
    0.85
    ামুটি
    0.83
     స్వాధీ
    0.83
    အစိတ်အပိုင်း
    0.82
     пищи
    0.81
    ランス
    0.81
    тын
    0.80
     পারিল
    0.79
    POSITIVE LOGITS
     yourself
    1.48
    0
    1.42
    l
    1.41
    H
    1.38
     Yourself
    1.27
    S
    1.26
    B
    1.17
     are
    1.16
    u
    1.16
    U
    1.16
    Act Density 0.892%

    No Known Activations