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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and code elements in a script

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

    variable assignments or questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Anerkennung
    -0.41
    Спољашње
    -0.39
    adaptiveStyles
    -0.38
     bedoeld
    -0.38
     nødvendig
    -0.36
     betweenstory
    -0.35
     invloed
    -0.35
     atualizado
    -0.35
     Vikipedi
    -0.34
    Voci
    -0.34
    POSITIVE LOGITS
    httphttps
    0.64
    ConstraintMaker
    0.59
    帖最后由
    0.47
     للاسماء
    0.47
     Italijani
    0.46
    +#+#
    0.46
    uckoo
    0.45
    AnchorTagHelper
    0.45
     defaultstate
    0.45
     stamps
    0.45
    Act Density 0.546%

    No Known Activations