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

    Neuronpedia

    INDEX
    Explanations

    natural light

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.54
     P
    0.54
     EVERY
    0.52
     J
    0.50
     E
    0.50
     this
    0.50
    ಾವಣ
    0.48
    ured
    0.47
    lin
    0.46
     j
    0.46
    POSITIVE LOGITS
     cidades
    0.65
    iciais
    0.61
    суз
    0.58
    ？](
    0.57
     gols
    0.57
    🏰
    0.55
    ières
    0.55
    presas
    0.55
    🏦
    0.55
     concili
    0.54
    Act Density 0.008%

    No Known Activations