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

    Neuronpedia

    INDEX
    Explanations

    reminder set

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    clickView
    0.60
    ğaz
    0.59
    リット
    0.56
     kaas
    0.56
     ಗೋ
    0.55
     تحصیل
    0.55
    隐含规则
    0.54
    فاع
    0.53
     clickView
    0.53
    зира
    0.53
    POSITIVE LOGITS
     set
    5.89
     Set
    5.52
    Set
    5.32
     sets
    5.23
    set
    5.20
     Sets
    4.84
     SET
    4.76
    SET
    4.70
    セット
    4.68
    Sets
    4.64
    Act Density 1.278%

    No Known Activations