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

    Neuronpedia

    INDEX
    Explanations

    re

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     iż
    0.92
    తీ
    0.79
    Immediate
    0.77
    これも
    0.75
     размеров
    0.74
    Excellent
    0.74
    Each
    0.74
     которыми
    0.73
    Although
    0.72
     केंद्रों
    0.71
    POSITIVE LOGITS
     unsure
    1.86
     trying
    1.50
     tired
    1.40
     nearing
    1.32
     unclear
    1.29
     faced
    1.27
     unable
    1.27
     uncertain
    1.26
     dealing
    1.24
     studying
    1.23
    Act Density 0.036%

    No Known Activations