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

    Neuronpedia

    INDEX
    Explanations

    peel, core, and quarter apples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鷸
    0.44
    Transparency
    0.44
    Training
    0.44
    咸
    0.43
    מן
    0.42
     myopia
    0.42
     Prepaid
    0.42
     predictive
    0.41
     monograph
    0.41
     شفاف
    0.41
    POSITIVE LOGITS
     fmt
    0.55
    forEach
    0.54
    core
    0.53
     tag
    0.52
    tag
    0.52
     core
    0.51
    fmt
    0.50
    <%@
    0.48
     CORE
    0.45
     Core
    0.44
    Act Density 0.010%

    No Known Activations