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

    Neuronpedia

    INDEX
    Explanations

    references to academic or scientific terms related to research and data analysis

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

    Follows nouns, often in technical or academic contexts

    np_acts-logits-general · gemini-2.0-flash

    components, patterns, resolution, solution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.88
     esetén
    -0.86
     ujednoznacz
    -0.84
     Houſe
    -0.67
    UserScript
    -0.66
     Diſ
    -0.66
    gendes
    -0.65
     sumpay
    -0.65
     Majefty
    -0.65
     Normdatei
    -0.63
    POSITIVE LOGITS
     itself
    1.02
    itself
    0.82
     of
    0.76
     portion
    0.74
     themselves
    0.73
     suivantes
    0.72
     Itself
    0.70
     aspect
    0.70
    iest
    0.65
    iniest
    0.64
    Act Density 3.719%

    No Known Activations