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

    Neuronpedia

    INDEX
    Explanations

    behavior

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    图形
    0.65
     ज्ञापन
    0.64
     公式
    0.64
    ညာ
    0.63
    éraux
    0.63
     เจ้า
    0.61
     பாடல்
    0.60
    ٗ
    0.60
     moistur
    0.60
    ຢ
    0.60
    POSITIVE LOGITS
     behavior
    4.27
     Behavior
    4.00
    Behavior
    3.94
     behaviour
    3.92
    behavior
    3.85
     behav
    3.77
     behaviors
    3.68
     Behaviour
    3.58
    behaviour
    3.47
     comportamiento
    3.46
    Act Density 0.373%

    No Known Activations