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

    Neuronpedia

    INDEX
    Explanations

    Code and snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ūsų
    -0.45
    RunWith
    -0.45
     Rudy
    -0.40
     viewDidLoad
    -0.40
    khó
    -0.39
     kohta
    -0.38
    bay
    -0.38
     song
    -0.38
     surla
    -0.38
    cinia
    -0.37
    POSITIVE LOGITS
     defaultstate
    0.75
     estimés
    0.75
     here
    0.74
    SourceChecksum
    0.72
     متعلقه
    0.68
     pride
    0.66
     snippetHide
    0.66
     InputDecoration
    0.65
     بيها
    0.64
     transfieras
    0.63
    Act Density 0.000%

    No Known Activations