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

    Neuronpedia

    INDEX
    Explanations

    learning and growth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informativa
    0.90
     half
    0.88
     tbsp
    0.86
     helped
    0.79
    oğlu
    0.79
    Half
    0.78
    ्रेंस
    0.78
    করণ
    0.77
     follow
    0.76
     Hälfte
    0.76
    POSITIVE LOGITS
    ஆ
    0.81
     कर्व
    0.78
    desk
    0.77
    ̷
    0.76
     Languages
    0.76
    Languages
    0.76
    ц
    0.75
    ディ
    0.75
    வைய
    0.74
     Calder
    0.74
    Act Density 0.141%

    No Known Activations