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

    Neuronpedia

    INDEX
    Explanations

    counting items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    0.82
     پہلی
    0.66
     provenance
    0.59
     방식
    0.59
     uku
    0.57
     massif
    0.56
    ینده
    0.56
     الدین
    0.55
    觧
    0.54
    קל
    0.54
    POSITIVE LOGITS
    into
    0.72
    atoms
    0.66
     tomto
    0.64
    student
    0.63
     bây
    0.62
    ell
    0.61
     nebo
    0.61
     малень
    0.59
    lap
    0.58
     Tomatoes
    0.58
    Act Density 0.317%

    No Known Activations