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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "up" and its variations in various contexts

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

    up to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     która
    -0.46
     doskon
    -0.44
     hormigón
    -0.43
    AntiForgeryToken
    -0.42
     ويكيپيديا
    -0.42
     mentre
    -0.42
     sessionFactory
    -0.42
     kebersihan
    -0.42
    .'.
    -0.41
    ®.
    -0.41
    POSITIVE LOGITS
     up
    1.23
     Up
    1.14
    Up
    1.05
    up
    1.02
     UP
    0.96
     ups
    0.91
     down
    0.83
     Ups
    0.80
    tup
    0.80
     DOWN
    0.80
    Act Density 0.055%

    No Known Activations