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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BM
    -0.07
    carry
    -0.07
    PF
    -0.07
     Nay
    -0.07
    .named
    -0.07
    칭
    -0.06
     fran
    -0.06
     Jah
    -0.06
    ب
    -0.06
    prefix
    -0.06
    POSITIVE LOGITS
     renting
    0.07
     differ
    0.07
    าเล
    0.07
     ≥
    0.06
     landscaping
    0.06
     confident
    0.06
    하다
    0.06
     terrace
    0.06
     tieten
    0.05
    んで
    0.05
    Act Density 0.007%

    No Known Activations