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

    Neuronpedia

    INDEX
    Explanations

    mathematical or pseudo-code expressions and syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens followed by specific letters

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbols and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.75
     مرئيه
    -0.73
     bezeichneter
    -0.70
    AutoresizingMask
    -0.69
    DropTable
    -0.65
     ſever
    -0.64
     ddelweddau
    -0.63
    abestanden
    -0.62
    DIPSETTING
    -0.62
    UserScript
    -0.61
    POSITIVE LOGITS
     p
    0.70
    p
    0.69
    c
    0.68
     S
    0.68
    b
    0.67
    s
    0.66
    e
    0.65
     b
    0.64
    t
    0.64
    y
    0.64
    Act Density 2.321%

    No Known Activations