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

    Neuronpedia

    INDEX
    Explanations

    tables, features, comparisons, and class

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Notiflix
    0.82
    usia
    0.76
    loadNpmTasks
    0.73
    them
    0.71
    嗮
    0.71
    璽
    0.67
    atakse
    0.66
    assapi
    0.66
    աստ
    0.66
     कहला
    0.66
    POSITIVE LOGITS
     |
    3.55
    |
    3.02
    |\
    2.41
    ｜
    2.29
     $|
    2.26
    |"
    2.24
    │
    2.24
     |\
    2.22
    |(
    2.20
     |-
    2.08
    Act Density 0.140%

    No Known Activations