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

    Neuronpedia

    INDEX
    Explanations

    knowledge update limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LayoutInflater
    0.40
     కీల
    0.40
    ிலை
    0.39
     patented
    0.38
    是他
    0.38
     Spice
    0.38
     المللی
    0.38
     latest
    0.38
     shaft
    0.38
     tweaked
    0.38
    POSITIVE LOGITS
    which
    0.52
    approximately
    0.46
    strange
    0.42
    zeit
    0.41
    stam
    0.41
     aproximadamente
    0.41
    adr
    0.40
    prof
    0.40
     novembro
    0.40
    ade
    0.39
    Act Density 0.052%

    No Known Activations