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

    Neuronpedia

    INDEX
    Explanations

    categories related to demographics and specific populations

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

    following "men" or "women"

    np_acts-logits-general · gemini-2.0-flash

    demographics and environments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ProcessEvent
    -0.54
    tagHelperRunner
    -0.53
     nahilalakip
    -0.52
     disambiguazione
    -0.51
     ujednoznacz
    -0.49
    OGND
    -0.49
    UseVisualStyle
    -0.48
     Defeat
    -0.47
    ivotopis
    -0.47
    WebVitals
    -0.47
    POSITIVE LOGITS
     يتيمه
    0.41
     especially
    0.40
     esternos
    0.37
    enumerable
    0.36
    especially
    0.36
    autant
    0.35
    cstdio
    0.34
    ########.
    0.33
     GetEnumerator
    0.33
     Особенно
    0.32
    Act Density 0.739%

    No Known Activations