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

    Neuronpedia

    INDEX
    Explanations

    beginner context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ticaret
    0.78
     resuspended
    0.77
    前面的
    0.77
    āra
    0.75
     கடந்த
    0.74
     ifs
    0.74
     epoca
    0.72
    atorios
    0.72
    rières
    0.71
     elapsed
    0.70
    POSITIVE LOGITS
     rejoice
    1.10
     extraordinaire
    1.08
     delight
    0.91
    ઓએ
    0.85
    Friendly
    0.84
    حث
    0.83
     upravo
    0.83
    Bible
    0.81
     looking
    0.81
    সক
    0.81
    Act Density 0.134%

    No Known Activations