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

    Neuronpedia

    INDEX
    Explanations

    structure for code or data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.55
    ك
    0.44
    시
    0.43
     at
    0.41
     ك
    0.41
     punkt
    0.41
    ){
    0.39
    Э
    0.39
     {})
    0.38
     جي
    0.38
    POSITIVE LOGITS
    riko
    0.41
    此同时
    0.39
    の変化
    0.38
    oucí
    0.37
    変更
    0.37
    lio
    0.37
    ordi
    0.37
    मधून
    0.37
    dings
    0.36
    aud
    0.36
    Act Density 0.222%

    No Known Activations