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

    Neuronpedia

    INDEX
    Explanations

    code and math formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    をした
    -0.07
     TLC
    -0.07
    _FOCUS
    -0.06
    伴
    -0.06
    iman
    -0.06
     από
    -0.06
    78
    -0.06
    _OPENGL
    -0.06
    まれ
    -0.06
     Pier
    -0.06
    POSITIVE LOGITS
    _hi
    0.07
     indicative
    0.06
     goat
    0.06
     ارزیابی
    0.06
     flux
    0.06
     levy
    0.06
    _std
    0.06
    Xd
    0.06
     accept
    0.06
    produk
    0.06
    Act Density 0.008%

    No Known Activations