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

    Neuronpedia

    INDEX
    Explanations

    user access and security

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pipe
    -0.08
     vegetarian
    -0.07
    Pipe
    -0.07
     incarceration
    -0.06
     Forget
    -0.06
     coefficients
    -0.06
    秀
    -0.06
    料無料
    -0.06
     shocks
    -0.06
    .$
    -0.06
    POSITIVE LOGITS
     edilen
    0.06
     первой
    0.06
     tak
    0.06
     gam
    0.06
    _ASSIGN
    0.06
     eslint
    0.06
     적용
    0.06
    :>
    0.06
     Poster
    0.06
    /assets
    0.06
    Act Density 0.033%

    No Known Activations