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

    Neuronpedia

    INDEX
    Explanations

    common words such as "the," "is," "of," "to," and "a."

    oai_token-act-pair · gemini-2.0-flash

    terms related to device modifications

    np_token-act-pair-logits · gpt-4o-mini

    modifications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     caras
    -0.48
     genoux
    -0.48
    arrol
    -0.48
     faccia
    -0.47
     planas
    -0.45
     scolaires
    -0.44
     buoni
    -0.44
     épaules
    -0.42
     normaux
    -0.42
     colorés
    -0.42
    POSITIVE LOGITS
     modification
    0.96
     modifications
    0.94
     Modification
    0.90
     conversions
    0.88
     Modifications
    0.87
     retrofit
    0.87
     additions
    0.86
     modify
    0.86
     conversion
    0.85
     install
    0.85
    Act Density 3.471%

    No Known Activations