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

    Neuronpedia

    INDEX
    Explanations

    prepositions and quantifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    距
    -0.07
     застос
    -0.06
    AE
    -0.06
    Gap
    -0.06
     okolí
    -0.06
    沿
    -0.06
     على
    -0.06
     ход
    -0.06
     daemon
    -0.06
    liga
    -0.06
    POSITIVE LOGITS
    歲
    0.07
     approximate
    0.06
     revised
    0.06
     sonic
    0.06
    .Work
    0.06
     profiling
    0.06
     Blazers
    0.06
     feu
    0.06
    سك
    0.06
     coli
    0.06
    Act Density 0.231%

    No Known Activations