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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and code-related terms

    oai_token-act-pair · gemini-2.0-flash

    varepsilon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     l
    -0.52
    Fe
    -0.48
     Fe
    -0.47
     centre
    -0.47
     j
    -0.47
     na
    -0.46
     n
    -0.45
    j
    -0.45
    fe
    -0.45
     d
    -0.44
    POSITIVE LOGITS
     Efq
    1.03
     Majefty
    1.01
     myſelf
    1.00
     Reſ
    0.95
     itſelf
    0.95
     Houſe
    0.94
     pleaſure
    0.94
     houſe
    0.94
    tvguidetime
    0.93
     ſeveral
    0.91
    Act Density 2.708%

    No Known Activations