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

    Neuronpedia

    INDEX
    Explanations

    writing or creating content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Create
    -0.55
     protect
    -0.53
     Save
    -0.51
     m
    -0.50
     Create
    -0.50
    Write
    -0.49
     pri
    -0.46
     
    -0.46
     protection
    -0.43
    Build
    -0.43
    POSITIVE LOGITS
    tagHelperRunner
    1.06
    GEBURTSDATUM
    1.05
     Мексичка
    1.02
    RenderAtEndOf
    0.97
     виправивши
    0.96
    Vidite
    0.95
     GenerationType
    0.92
    SourceChecksum
    0.91
    OGND
    0.90
    TestingModule
    0.87
    Act Density 0.262%

    No Known Activations