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

    Neuronpedia

    INDEX
    Explanations

    partially in shadow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     developed
    0.46
     Fukushima
    0.46
     Infinite
    0.45
     preservatives
    0.45
     unbounded
    0.45
     modernist
    0.45
     external
    0.44
     preserved
    0.44
     Lake
    0.43
     Departments
    0.43
    POSITIVE LOGITS
    و
    0.53
    رة
    0.52
     ajuste
    0.48
    hun
    0.46
    緝
    0.46
     cristianos
    0.45
    леко
    0.44
    getConfig
    0.44
    หล
    0.44
    ದ್ಯ
    0.44
    Act Density 0.001%

    No Known Activations