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

    Neuronpedia

    INDEX
    Explanations

    e

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trải
    -0.07
    .Ε
    -0.07
    ề
    -0.06
    ysqli
    -0.06
     hurting
    -0.06
    awe
    -0.06
    門
    -0.06
    agus
    -0.06
     Retail
    -0.06
    (Return
    -0.06
    POSITIVE LOGITS
     ###↵
    0.07
     dây
    0.07
     Oktober
    0.06
     اک
    0.06
    \Mail
    0.06
    Fizz
    0.06
    Characters
    0.06
    -gl
    0.06
    Flags
    0.06
     причины
    0.06
    Act Density 0.000%

    No Known Activations