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

    Neuronpedia

    INDEX
    Explanations

    terms and expressions related to health, wellness, and safety

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

    ending in "l"

    np_acts-logits-general · gemini-2.0-flash

    chemical suffixes and word endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    syntax
    -0.41
    AutoScaleMode
    -0.40
    İŞ
    -0.39
    uros
    -0.38
    нали
    -0.38
    INAL
    -0.37
    sians
    -0.37
    iddish
    -0.35
     rising
    -0.35
    ERING
    -0.34
    POSITIVE LOGITS
    lable
    0.74
    led
    0.73
    ling
    0.68
    l
    0.68
    ｌ
    0.66
    ℓ
    0.65
    ls
    0.65
    lapp
    0.63
    let
    0.63
    lof
    0.62
    Act Density 0.588%

    No Known Activations