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

    Neuronpedia

    INDEX
    Explanations

    comfortable with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Vide
    0.91
     हैप्पी
    0.91
     सुप्रभात
    0.84
    মধ
    0.82
     Aquaculture
    0.81
     Vide
    0.80
     implicate
    0.80
     hydroph
    0.79
    Tesla
    0.78
     சிறப்பு
    0.77
    POSITIVE LOGITS
    ez
    0.90
     പിന്നീട്
    0.87
     তারপরে
    0.86
     voulait
    0.84
     também
    0.81
     segurança
    0.80
     তারপর
    0.80
     scolded
    0.79
     shouted
    0.78
    ומר
    0.78
    Act Density 0.000%

    No Known Activations