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

    Neuronpedia

    INDEX
    Explanations

    imperceptible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    flake
    0.89
     Macbook
    0.86
     iPhones
    0.85
     rok
    0.79
     létre
    0.78
     Macintosh
    0.77
     católica
    0.77
     inguinal
    0.77
     básica
    0.77
     MBP
    0.77
    POSITIVE LOGITS
    ص
    0.74
     repairs
    0.74
    ر
    0.74
    民
    0.70
    стема
    0.68
    ਆ
    0.67
    ل
    0.66
    з
    0.66
     pleads
    0.65
    ED
    0.65
    Act Density 0.000%

    No Known Activations