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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases related to document status and updates

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

    errors and changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pantalones
    -0.62
    RenderAtEndOf
    -0.54
     Савезне
    -0.54
    الحياه
    -0.52
    SequentialGroup
    -0.50
    lapsingToolbar
    -0.49
    PreInfinity
    -0.49
    OGND
    -0.48
    RTEX
    -0.48
    +#+
    -0.47
    POSITIVE LOGITS
     changes
    0.46
     changements
    0.41
     సౌకర్య
    0.40
     cambios
    0.39
     față
    0.37
     mistakes
    0.37
     errors
    0.36
     imperfections
    0.36
     bugs
    0.35
     InputMaybe
    0.35
    Act Density 0.010%

    No Known Activations