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

    Neuronpedia

    INDEX
    Explanations

    references to foundational concepts or entities

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

    "ground" and following words

    np_acts-logits-general · gemini-2.0-flash

    ground state or floor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.84
    évaluateur
    -0.59
    Espèce
    -0.58
    adaptiveStyles
    -0.55
    iodía
    -0.53
    PreferredItem
    -0.51
    expandindo
    -0.50
     gyer
    -0.50
    LookAnd
    -0.49
     समीक्षाओं
    -0.49
    POSITIVE LOGITS
    hog
    0.82
    swell
    0.82
     floor
    0.73
     truth
    0.73
    breaking
    0.71
    hogs
    0.69
    Truth
    0.66
     Floor
    0.65
    HOG
    0.65
    truth
    0.64
    Act Density 0.079%

    No Known Activations