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

    Neuronpedia

    INDEX
    Explanations

    non-numeric characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     baptism
    0.78
     Bapt
    0.77
     удиви
    0.76
     baptized
    0.76
     sitten
    0.75
     три
    0.75
     microbiology
    0.74
     Lula
    0.74
     loneliness
    0.74
     пять
    0.73
    POSITIVE LOGITS
    Only
    1.20
    For
    1.04
    Unlike
    1.03
    Because
    0.99
    Non
    0.96
    Generally
    0.95
    Since
    0.95
    While
    0.91
    非
    0.91
    non
    0.90
    Act Density 0.343%

    No Known Activations