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

    Neuronpedia

    INDEX
    Explanations

    ABC news and television

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.75
    a
    0.57
    est
    0.55
    je
    0.52
    ये
    0.51
     excretion
    0.51
    cate
    0.51
    in
    0.50
    lets
    0.50
    were
    0.50
    POSITIVE LOGITS
    ﻌ
    0.67
    ".$
    0.59
    ⸱
    0.59
    ﻮ
    0.58
     intercal
    0.57
     stabilité
    0.57
     bulunan
    0.57
    ંદ્ર
    0.56
    LookAndFeel
    0.55
     instancia
    0.55
    Act Density 0.000%

    No Known Activations