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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     comigo
    0.42
     contigo
    0.41
    ंथ
    0.39
    ein
    0.38
    ote
    0.37
    انو
    0.37
     compel
    0.36
    Context
    0.36
    ायला
    0.36
     Bailey
    0.36
    POSITIVE LOGITS
     удар
    0.46
     ओह
    0.42
     தல
    0.41
    优雅
    0.41
    ।]
    0.40
    рях
    0.39
     slechts
    0.38
     வண
    0.38
    সাং
    0.38
    统
    0.38
    Act Density 0.000%

    No Known Activations