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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific terms related to coding or configuration contexts

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

    names like Yong and Clarence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Maul
    -0.42
     prêtres
    -0.42
     Partager
    -0.41
    1
    -0.38
     Priester
    -0.37
    3
    -0.36
    inOrder
    -0.36
     rosado
    -0.35
    -
    -0.35
     Juifs
    -0.35
    POSITIVE LOGITS
     Yong
    1.02
     Leroy
    1.02
    Yong
    1.00
    yong
    0.94
    Leroy
    0.87
    amethasone
    0.73
     yong
    0.68
     NYS
    0.62
     للاسماء
    0.61
    bleau
    0.60
    Act Density 0.016%

    No Known Activations