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

    Neuronpedia

    INDEX
    Explanations

    discomfort and issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Oxy
    0.53
    ConfigRequest
    0.49
     Vivi
    0.49
     সম্পর্কে
    0.48
     офі
    0.48
     つ
    0.48
     hidup
    0.47
    терна
    0.47
    على
    0.47
     공식
    0.47
    POSITIVE LOGITS
    b
    0.53
    k
    0.44
    糕
    0.42
     outlets
    0.41
    v
    0.41
     handlers
    0.41
    d
    0.41
    kai
    0.41
    가
    0.40
     practitioners
    0.40
    Act Density 0.002%

    No Known Activations