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

    Neuronpedia

    INDEX
    Explanations

    function definition arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     etiqu
    0.57
     rejo
    0.51
     joys
    0.51
     disheart
    0.50
    '
    0.50
     underval
    0.50
    (“
    0.50
     silage
    0.49
     plotly
    0.49
     VLAN
    0.49
    POSITIVE LOGITS
     લગભગ
    0.43
    อฟ
    0.42
    را
    0.41
    zd
    0.40
    BUSINESS
    0.40
    DateTimePicker
    0.40
    팜
    0.40
    Ops
    0.39
    PerHour
    0.39
    پ
    0.39
    Act Density 0.001%

    No Known Activations