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

    Neuronpedia

    INDEX
    Explanations

    furnace and Mono

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.91
    stays
    0.76
    r
    0.71
    ul
    0.71
    an
    0.70
    thed
    0.69
    the
    0.68
    m
    0.62
    tle
    0.61
    tob
    0.61
    POSITIVE LOGITS
     poet
    0.55
    ના
    0.55
     peut
    0.55
     Citt
    0.54
    achter
    0.53
    ात्
    0.52
     como
    0.52
     advert
    0.52
     religion
    0.52
    Puede
    0.52
    Act Density 0.000%

    No Known Activations