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

    Neuronpedia

    INDEX
    Explanations

    varied text and code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Character
    -0.07
     Số
    -0.07
    Variables
    -0.06
     рецепт
    -0.06
     plots
    -0.06
     liberties
    -0.06
     من
    -0.06
     Intel
    -0.06
     pairwise
    -0.06
     τα
    -0.06
    POSITIVE LOGITS
     elimin
    0.06
     öld
    0.06
    .prev
    0.06
     bake
    0.06
     Souls
    0.06
    нез
    0.06
    _NON
    0.06
    tul
    0.06
     triang
    0.06
    .",↵
    0.06
    Act Density 0.160%

    No Known Activations