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

    Neuronpedia

    INDEX
    Explanations

    references to evaluation and assessment guidelines in a scientific context

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

    data collection and analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UrlResolution
    -0.39
    httphttps
    -0.38
     définiti
    -0.38
     صوتيه
    -0.33
     inv
    -0.32
     keter
    -0.32
     bug
    -0.32
    bility
    -0.31
     miracle
    -0.31
    -0.31
    POSITIVE LOGITS
     exposure
    0.69
     Exposure
    0.65
     ventilation
    0.63
    Exposure
    0.60
    InitVars
    0.59
    GIH
    0.59
     exposures
    0.58
    exposure
    0.58
     respirator
    0.56
     Expos
    0.55
    Act Density 0.000%

    No Known Activations