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

    Neuronpedia

    INDEX
    Explanations

    simple descriptive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reductase
    0.82
    𝙉
    0.78
     attacc
    0.75
     Ilana
    0.74
     Ако
    0.72
    зор
    0.71
     ISZ
    0.71
    魎
    0.71
    ration
    0.71
    Ƒ
    0.70
    POSITIVE LOGITS
     suffice
    0.68
    k
    0.65
    o
    0.63
     demeanor
    0.63
     محک
    0.63
     senc
    0.62
     pleasures
    0.62
     methodical
    0.62
     chic
    0.61
    t
    0.61
    Act Density 0.820%

    No Known Activations