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

    Neuronpedia

    INDEX
    Explanations

    non-English, code, abbreviations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    InputTagHelper
    -0.56
    SourceChecksum
    -0.50
    ەی
    -0.49
    RenderAtEndOf
    -0.49
    HAM
    -0.48
    DeleteCommand
    -0.45
    Siren
    -0.44
    tilhe
    -0.44
    radio
    -0.44
    udsman
    -0.43
    POSITIVE LOGITS
    AccessorTable
    0.64
    $_['
    0.63
     виправивши
    0.60
     ROE
    0.56
    medriver
    0.51
    RetentionPolicy
    0.51
     neige
    0.49
     nourrir
    0.49
    SpringBootTest
    0.49
    цездатний
    0.49
    Act Density 0.000%

    No Known Activations