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

    Neuronpedia

    INDEX
    Explanations

    scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FONT
    -0.07
    -striped
    -0.07
     charter
    -0.07
     Billy
    -0.06
    Theme
    -0.06
    .Initial
    -0.06
     zde
    -0.06
     tội
    -0.06
    .keyboard
    -0.06
     Kum
    -0.06
    POSITIVE LOGITS
     RHS
    0.06
    ’,
    0.06
    äll
    0.06
    _;↵
    0.06
    _,
    0.06
    emodel
    0.06
    だった
    0.06
    νομ
    0.06
     blas
    0.06
     départ
    0.06
    Act Density 0.134%

    No Known Activations