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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    比
    -0.07
     correcting
    -0.07
    Cr
    -0.07
    าผ
    -0.07
    Ma
    -0.06
    それは
    -0.06
    [to
    -0.06
    639
    -0.06
    اشت
    -0.06
     LoginForm
    -0.06
    POSITIVE LOGITS
     ευ
    0.06
    ULLET
    0.06
    .ndim
    0.06
     ';
    0.06
    angi
    0.06
     اقتص
    0.06
     نويسنده
    0.06
    народ
    0.06
     ';↵
    0.06
    ς
    0.06
    Act Density 0.025%

    No Known Activations