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

    Neuronpedia

    INDEX
    Explanations

    be expected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     glories
    1.31
     usefulness
    1.27
     pesky
    1.24
    i
    1.19
     oferty
    1.16
     vandalism
    1.15
     finitely
    1.15
     unpredict
    1.15
     harassing
    1.10
     hesitation
    1.09
    POSITIVE LOGITS
    ้น
    0.95
     punte
    0.92
    ة
    0.92
     cáps
    0.92
    ция
    0.88
    ্লোক
    0.87
    య
    0.86
     perquè
    0.86
    හ
    0.85
    Ÿ
    0.84
    Act Density 0.000%

    No Known Activations