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

    Neuronpedia

    INDEX
    Explanations

    final answer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     αγο
    0.33
    सार
    0.33
     рестора
    0.32
     दया
    0.31
    圄
    0.31
     लौट
    0.31
     parce
    0.31
    헙
    0.30
    Ꮤ
    0.30
     acredit
    0.30
    POSITIVE LOGITS
    رق
    0.29
    nels
    0.27
    chan
    0.27
     Pancake
    0.27
    propelled
    0.27
    anément
    0.26
    slee
    0.26
    CurrentByte
    0.26
     Parkinson
    0.26
     potentiometer
    0.26
    Act Density 0.066%

    No Known Activations