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

    Neuronpedia

    INDEX
    Explanations

    unique identifiers or attributes typically associated with profiles or personal information

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

    multi-lingual words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Vidite
    -0.50
    TemporalType
    -0.46
    zło
    -0.46
     Мексичка
    -0.45
    ophyllum
    -0.43
    šlo
    -0.40
    EndGlobalSection
    -0.40
    шло
    -0.40
    └──
    -0.38
    лось
    -0.38
    POSITIVE LOGITS
     himself
    0.66
     kasarigan
    0.61
    himself
    0.60
     himſelf
    0.56
    ArgumentParser
    0.55
     eenen
    0.54
     Grecs
    0.51
    🇶
    0.49
    OGND
    0.47
    ConstraintMaker
    0.47
    Act Density 0.011%

    No Known Activations