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

    Neuronpedia

    INDEX
    Explanations

    status or area of focus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.60
    '
    0.54
    }
    0.53
    6
    0.50
     six
    0.48
    ↵
    0.48
    8
    0.48
    ]
    0.47
    L
    0.47
    debug
    0.46
    POSITIVE LOGITS
     kiddos
    0.77
     તેમજ
    0.75
     sekä
    0.64
     ataupun
    0.61
     কিংবা
    0.60
     које
    0.58
     içerisinde
    0.58
    casted
    0.58
     ciò
    0.57
    だけでなく
    0.57
    Act Density 0.016%

    No Known Activations