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

    Neuronpedia

    INDEX
    Explanations

    Wikipedia references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wikipedia
    1.09
     wikipedia
    1.07
     wiki
    1.03
    wiki
    0.96
    Wiki
    0.94
     Wiki
    0.94
     pomocą
    0.92
    wikipedia
    0.92
     Вики
    0.90
     wikip
    0.89
    POSITIVE LOGITS
     fenomeni
    0.91
    日英
    0.84
     обуча
    0.83
    🅔
    0.83
    fonos
    0.82
    дная
    0.82
     hole
    0.81
    독
    0.80
     Rafał
    0.80
    dDays
    0.78
    Act Density 0.003%

    No Known Activations