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

    Neuronpedia

    INDEX
    Explanations

    Googlepersonal information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vrijwilli
    -0.84
     Jumlah
    -0.84
     Perubahan
    -0.77
     男孩
    -0.76
     Terkait
    -0.73
     Tempat
    -0.73
     Manusia
    -0.73
    炷
    -0.72
    alami
    -0.72
    感知
    -0.72
    POSITIVE LOGITS
    culin
    0.94
     vī
    0.84
    Ḱ
    0.83
    wet
    0.81
    amma
    0.79
    );"
    0.78
    eck
    0.76
     ALPH
    0.76
     Geraadpleegd
    0.75
     tikai
    0.75
    Act Density 0.008%

    No Known Activations