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

    Neuronpedia

    INDEX
    Explanations

    there

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    цать
    -0.50
     was
    -0.48
     vero
    -0.47
     débat
    -0.46
     fallu
    -0.45
     there
    -0.45
     agreed
    -0.45
    ۇ
    -0.44
     looked
    -0.43
     seemed
    -0.43
    POSITIVE LOGITS
    BrowserModule
    0.76
    ondissement
    0.74
    tvguidetime
    0.73
    ValueGeneration
    0.72
    AndEndTag
    0.71
     snippetHide
    0.68
    homonymie
    0.66
    KURZBESCHREIBUNG
    0.65
    migrationBuilder
    0.65
    ModelBuilder
    0.64
    Act Density 0.000%

    No Known Activations