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

    Neuronpedia

    INDEX
    Explanations

    list items following commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tablespoons
    0.88
    ในช่วง
    0.80
    客様
    0.79
    grapes
    0.79
     eds
    0.79
    ાર્થી
    0.79
     ISPs
    0.78
     acorns
    0.77
     assays
    0.77
     учреждений
    0.76
    POSITIVE LOGITS
    ح
    1.31
    ك
    1.29
    ق
    1.09
    غ
    1.05
    ח
    0.93
    د
    0.88
    ول
    0.88
    га
    0.87
    í
    0.87
    دون
    0.86
    Act Density 0.000%

    No Known Activations