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

    Neuronpedia

    INDEX
    Explanations

    numbers, dates and percentages

    oai_token-act-pair · gemini-2.0-flash

    1, 3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     the
    -0.74
    EFIAPI
    -0.68
    WithIOException
    -0.67
    wapV
    -0.67
     оригіналу
    -0.59
    Pranala
    -0.59
    WarningLevel
    -0.57
     utafitiHapana
    -0.57
     Patil
    -0.57
     cast
    -0.57
    POSITIVE LOGITS
     Theſe
    0.96
     houſe
    0.96
     iſt
    0.91
     Jefus
    0.90
     XNUMX
    0.83
     ſche
    0.82
     itſelf
    0.82
     Majefty
    0.82
    atorze
    0.81
     myſelf
    0.81
    Act Density 3.981%

    No Known Activations