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

    Neuronpedia

    INDEX
    Explanations

    Substance Abuse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     funções
    0.36
    adinya
    0.36
     माली
    0.36
     റ
    0.36
    雰
    0.36
     Dubey
    0.35
     стаби
    0.35
     pesso
    0.35
    کنند
    0.35
    +",
    0.35
    POSITIVE LOGITS
     fag
    0.49
    ogon
    0.42
    getCount
    0.41
     Gonz
    0.39
     NSObject
    0.38
     cmp
    0.38
    cmp
    0.37
    甃
    0.37
    봉
    0.37
     pit
    0.36
    Act Density 0.001%

    No Known Activations