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

    Neuronpedia

    INDEX
    Explanations

    page

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    руд
    -0.07
     rept
    -0.07
     ayon
    -0.07
     വിശ
    -0.07
    Column
    -0.07
    volved
    -0.07
    ricos
    -0.07
     líquidos
    -0.07
    .RE
    -0.07
    rex
    -0.07
    POSITIVE LOGITS
     placeholder
    0.11
    placeholder
    0.11
    _placeholder
    0.11
    Placeholder
    0.10
    .placeholder
    0.10
    -placeholder
    0.10
     Placeholder
    0.10
     interim
    0.10
     preliminary
    0.09
    暂
    0.09
    Act Density 0.004%

    No Known Activations