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

    Neuronpedia

    INDEX
    Explanations

    long-term holding periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.82
    0
    0.74
    )
    0.72
    ك
    0.71
     courageous
    0.71
    0.70
    潑
    0.69
     حافظ
    0.66
    ton
    0.66
    skich
    0.66
    POSITIVE LOGITS
    াহতি
    0.91
    jač
    0.84
     Directeur
    0.83
    졍
    0.83
     रोगों
    0.82
    のですが
    0.81
    はこの
    0.81
     Inicio
    0.80
     সেনাবাহ
    0.80
     Educación
    0.79
    Act Density 0.000%

    No Known Activations