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

    Neuronpedia

    INDEX
    Explanations

    expressions of confusion and disagreement

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

    asking questions or seeking clarification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wikiseite
    -0.54
     للاسماء
    -0.52
     monasterio
    -0.51
     muñecas
    -0.50
     saveiro
    -0.49
     препратки
    -0.49
    Geplaatst
    -0.49
     anún
    -0.48
     pelúcia
    -0.48
    majánló
    -0.47
    POSITIVE LOGITS
     Beck
    0.48
     ur
    0.47
     Gallo
    0.46
     Mr
    0.46
     Hook
    0.44
     mr
    0.42
     ball
    0.42
     „
    0.42
     Ang
    0.42
     ang
    0.41
    Act Density 0.201%

    No Known Activations