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

    Neuronpedia

    INDEX
    Explanations

    questions

    oai_token-act-pair · gemini-2.0-flash

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     what
    -2.03
    what
    -1.84
    What
    -1.72
     What
    -1.65
    <bos>
    -1.50
     WHAT
    -1.45
    WHAT
    -1.37
     whats
    -1.18
    whats
    -1.14
     Whats
    -1.05
    POSITIVE LOGITS
    IonicModule
    0.57
    DOCTYPE
    0.56
     BorderRadius
    0.55
    ámara
    0.54
    ConverterFactory
    0.54
     Himo
    0.52
    verwijspagina
    0.52
    perity
    0.52
    setTypeface
    0.51
    UnsafeEnabled
    0.51
    Act Density 1.451%

    No Known Activations