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

    Neuronpedia

    INDEX
    Explanations

    / science

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Crack
    0.82
     charm
    0.77
     گزار
    0.72
     charms
    0.71
     crack
    0.69
     bilan
    0.68
     worked
    0.68
    ci
    0.66
     क्लासेस
    0.66
     missp
    0.66
    POSITIVE LOGITS
    ově
    0.77
    ⠊
    0.74
    }$')
    0.71
    僟
    0.71
     지속
    0.67
     Roskov
    0.66
    ^{-/-}$
    0.66
    দ্বীপ
    0.66
     آغاز
    0.65
    adventure
    0.65
    Act Density 0.004%

    No Known Activations