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

    Neuronpedia

    INDEX
    Explanations

    Code/Dictionary snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.65
    #+#
    -0.53
    ScopeManager
    -0.53
     dict
    -0.52
    ViewFeatures
    -0.52
    enty
    -0.51
     Réponses
    -0.49
     PyLong
    -0.49
    e
    -0.48
    migrationBuilder
    -0.47
    POSITIVE LOGITS
    dicionado
    0.65
     ligiloj
    0.59
    SharedCtor
    0.58
    osoba
    0.57
     opérateur
    0.55
     himo
    0.52
     isInitialized
    0.52
     OO
    0.51
    oplasma
    0.51
    lyn
    0.50
    Act Density 0.701%

    No Known Activations