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

    Neuronpedia

    INDEX
    Explanations

    import, hugging, App

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Control
    0.64
    控
    0.60
     걸
    0.58
     Lead
    0.58
     trap
    0.58
     props
    0.58
     gecko
    0.57
     농
    0.56
     次元
    0.56
     drops
    0.55
    POSITIVE LOGITS
    LastError
    0.62
    Outer
    0.60
    Microelectronics
    0.60
     सीएस
    0.58
    lenia
    0.58
    níky
    0.58
     ու
    0.57
    切
    0.57
    Callories
    0.57
    plates
    0.55
    Act Density 0.111%

    No Known Activations