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

    Neuronpedia

    INDEX
    Explanations

    image processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     लिए
    0.94
    וש
    0.93
    ことで
    0.88
     أهم
    0.88
     में
    0.87
     большинстве
    0.82
    的
    0.82
    聵
    0.82
     แ
    0.81
     있는
    0.80
    POSITIVE LOGITS
     oiseaux
    1.03
     rhenium
    0.97
    8
    0.97
    9
    0.96
    5
    0.94
    4
    0.93
     salido
    0.89
    6
    0.89
     cuisses
    0.86
     smoke
    0.82
    Act Density 0.085%

    No Known Activations