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

    Neuronpedia

    INDEX
    Explanations

    apple event

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stably
    0.43
     flat
    0.43
     HOMO
    0.42
    ופ
    0.40
     perfused
    0.40
     valley
    0.39
     clocked
    0.39
     multi
    0.39
     delf
    0.39
     expanse
    0.39
    POSITIVE LOGITS
    বুঝ
    0.47
    ුණ
    0.46
     सरफेस
    0.42
    ênt
    0.42
    Look
    0.41
    ሃኒ
    0.40
     Authentication
    0.39
     нужда
    0.39
     trồng
    0.39
     Providers
    0.39
    Act Density 0.005%

    No Known Activations