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

    Neuronpedia

    INDEX
    Explanations

    working

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _NOP
    -0.07
    ेर
    -0.07
    anggan
    -0.07
     России
    -0.06
    .rooms
    -0.06
     الاتحاد
    -0.06
    ک
    -0.06
    31
    -0.06
    _four
    -0.06
     उद
    -0.06
    POSITIVE LOGITS
    -heavy
    0.08
    .");↵↵
    0.07
     ",
    0.07
    拼
    0.06
     severe
    0.06
     bring
    0.06
     backgroundImage
    0.06
    FL
    0.06
     ई
    0.06
    Martin
    0.06
    Act Density 0.146%

    No Known Activations