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

    Neuronpedia

    INDEX
    Explanations

    Pacific Ocean

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tik
    0.78
    0.77
    t
    0.75
    the
    0.74
    ainkan
    0.73
    và
    0.72
     utilises
    0.71
     marginalised
    0.70
     Rosso
    0.70
     maju
    0.68
    POSITIVE LOGITS
    的
    0.84
    ة
    0.82
    ת
    0.80
    ים
    0.77
    ૧
    0.72
    ೧
    0.69
    鳖
    0.69
    同
    0.68
    ปี
    0.68
    他
    0.68
    Act Density 0.001%

    No Known Activations