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

    Neuronpedia

    INDEX
    Explanations

    academic citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     checkboxes
    0.40
     scooters
    0.38
     hammers
    0.38
     Scotts
    0.37
    Đặt
    0.37
     aisles
    0.37
    Switcher
    0.36
    ⓶
    0.36
     flamingo
    0.36
    逊
    0.36
    POSITIVE LOGITS
    citation
    0.41
    g
    0.39
     본
    0.38
    5
    0.37
    r
    0.37
    8
    0.37
    9
    0.36
    cite
    0.36
    ara
    0.36
    6
    0.35
    Act Density 0.004%

    No Known Activations