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

    Neuronpedia

    INDEX
    Explanations

    numeric values and their associated contexts

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

    Numbers around 300,000 or less

    np_acts-logits-general · gemini-2.0-flash

    numbers in the thousands and millions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ERSITY
    -0.64
     RSITY
    -0.64
    });*/
    -0.58
    iffance
    -0.58
     Bén
    -0.56
    VERTISEMENT
    -0.56
    HICLE
    -0.56
    oxidase
    -0.56
    └──
    -0.55
    }*/
    -0.54
    POSITIVE LOGITS
    featureID
    0.75
    AddTagHelper
    0.73
    PyExc
    0.73
    mybatisplus
    0.71
    bootstrapcdn
    0.71
    PreferredItem
    0.68
     للمعارف
    0.68
    0
    0.67
    rungsseite
    0.65
    DeleteBehavior
    0.64
    Act Density 0.059%

    No Known Activations