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

    Neuronpedia

    INDEX
    Explanations

    to set up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    మని
    0.60
     моги
    0.58
     ಗೋ
    0.56
    ğaz
    0.56
    ونکي
    0.55
    PlatformImage
    0.55
     تحصیل
    0.55
     kaas
    0.55
    phalodes
    0.55
    ಂಚ
    0.54
    POSITIVE LOGITS
     set
    5.26
     Set
    5.00
    Set
    4.83
     sets
    4.73
    set
    4.71
     setting
    4.52
     Sets
    4.46
     SET
    4.44
     Setting
    4.38
    SET
    4.36
    Act Density 0.699%

    No Known Activations