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

    Neuronpedia

    INDEX
    Explanations

    .

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مزید
    0.75
     hiccups
    0.72
    شك
    0.69
     cilia
    0.68
     aggravation
    0.68
     fanfare
    0.68
     discontinued
    0.67
     ফিরিয়ে
    0.67
     indigo
    0.67
     alleviated
    0.66
    POSITIVE LOGITS
    In
    0.63
    whose
    0.62
    faced
    0.61
    Would
    0.59
    n
    0.58
    面对
    0.57
    B
    0.56
    ৈ
    0.55
     In
    0.54
    can
    0.53
    Act Density 0.458%

    No Known Activations