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

    Neuronpedia

    INDEX
    Explanations

    racist content filtering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Zaj
    0.39
    ိုင်
    0.39
     manglid
    0.38
     হাউ
    0.38
     Trout
    0.38
    ają
    0.37
     Zayed
    0.36
     manifest
    0.36
     Mục
    0.36
     manifi
    0.36
    POSITIVE LOGITS
     Larsen
    0.41
     ome
    0.40
     peg
    0.38
     Rope
    0.38
    িয়ের
    0.38
     buffer
    0.36
    เท
    0.36
    plex
    0.35
     Peg
    0.35
    Peg
    0.35
    Act Density 0.004%

    No Known Activations