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

    Neuronpedia

    INDEX
    Explanations

    break down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अथवा
    0.60
    themed
    0.59
     ചില
    0.58
     چند
    0.56
    Support
    0.55
     โ
    0.55
     פ
    0.55
     ఏర్పాటు
    0.54
    ク
    0.54
     یا
    0.54
    POSITIVE LOGITS
     only
    0.73
     hanya
    0.68
    実際の
    0.68
    ですから
    0.67
     says
    0.62
     so
    0.61
     actual
    0.61
     только
    0.61
     Only
    0.60
     intuit
    0.60
    Act Density 0.759%

    No Known Activations