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

    Neuronpedia

    INDEX
    Explanations

    second

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    })
    0.62
    8
    0.62
    6
    0.61
     theses
    0.57
     we
    0.56
     you
    0.54
     all
    0.54
    9
    0.54
     थे
    0.53
     अं
    0.50
    POSITIVE LOGITS
     second
    1.14
    第二
    1.12
     Second
    1.10
    Second
    1.08
    second
    1.06
     segunda
    1.05
     ikinci
    1.03
     deuxième
    1.02
     secondary
    1.00
     Secondary
    0.98
    Act Density 0.031%

    No Known Activations