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

    Neuronpedia

    INDEX
    Explanations

    villages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Diy
    -0.08
    born
    -0.08
    男
    -0.07
    uring
    -0.07
    Comments
    -0.06
     grooming
    -0.06
    _OTHER
    -0.06
    ꕥ
    -0.06
    情趣
    -0.06
    🤨
    -0.06
    POSITIVE LOGITS
     proteins
    0.07
     Elsa
    0.07
     المستقبل
    0.07
     Santana
    0.07
    Castle
    0.07
    毫无疑问
    0.07
    ⁑
    0.07
    (opts
    0.07
    ℘
    0.06
    _gateway
    0.06
    Act Density 0.031%

    No Known Activations