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

    Neuronpedia

    INDEX
    Explanations

    you know, you've hit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    μένη
    0.87
     ous
    0.87
     Dec
    0.85
     时尚
    0.82
     interracial
    0.78
     mùa
    0.77
    InMillis
    0.76
     Yugoslav
    0.76
     fused
    0.76
    erus
    0.74
    POSITIVE LOGITS
    sensors
    0.97
    Documents
    0.96
    arquivo
    0.96
     सीआर
    0.96
     தாம்
    0.91
    றுத்த
    0.90
    ड्र
    0.89
    不支持
    0.89
    記述
    0.89
     несу
    0.89
    Act Density 0.045%

    No Known Activations