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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "weak" in various contexts

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

    weak case, LICENSE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tanleria
    -0.65
     surla
    -0.50
    Manbalar
    -0.45
    antwortung
    -0.45
    sidemargin
    -0.44
    ----</
    -0.43
    aternion
    -0.42
     Italijanski
    -0.42
    rrggbb
    -0.41
     AppBundle
    -0.41
    POSITIVE LOGITS
    weak
    2.41
     Weak
    2.19
    Weak
    2.16
     weak
    2.13
    WEAK
    1.63
     weakly
    1.57
     weakness
    1.48
     weaker
    1.44
    弱
    1.41
     débil
    1.40
    Act Density 0.003%

    No Known Activations