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

    Neuronpedia

    INDEX
    Explanations

    numbers and related terms in scientific notation and experimental design

    oai_token-act-pair · gemini-2.0-flash

    Scientific notations and maths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🏾
    -0.52
    an
    -0.49
    j
    -0.47
    🏻
    -0.46
    sta
    -0.44
    asties
    -0.44
    charCodeAt
    -0.43
    fq
    -0.42
    /***/
    -0.42
    du
    -0.41
    POSITIVE LOGITS
    e
    2.13
    E
    1.31
    eze
    0.94
    eit
    0.87
    eet
    0.86
    eo
    0.82
    eis
    0.82
    eer
    0.81
    ezy
    0.81
    ein
    0.80
    Act Density 11.509%

    No Known Activations