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

    Neuronpedia

    INDEX
    Explanations

    references to specific measurements or terms related to physics and engineering

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

    Kazakhstan nuggets, modulus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Stowe
    -0.41
     Clay
    -0.40
    Clay
    -0.40
    beruf
    -0.39
     Champlain
    -0.39
     Sprachen
    -0.38
    compat
    -0.35
     Vie
    -0.35
    Vie
    -0.35
     Maria
    -0.34
    POSITIVE LOGITS
     Nuggets
    2.02
     nuggets
    1.80
    uggets
    1.77
     nugget
    1.71
    ugget
    1.70
     Nug
    0.77
    uggest
    0.61
     оригіналу
    0.57
    ugges
    0.55
    theless
    0.54
    Act Density 0.001%

    No Known Activations