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

    Neuronpedia

    INDEX
    Explanations

    bing chat or image

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ig
    0.90
    ل
    0.89
    ून
    0.88
    EVER
    0.83
    in
    0.83
    p
    0.82
    ndrome
    0.80
    nden
    0.79
    mod
    0.79
    CHAR
    0.79
    POSITIVE LOGITS
     funcionários
    1.02
     existência
    0.94
     presión
    0.92
     وإ
    0.91
     associação
    0.89
     mulberry
    0.88
     ilusión
    0.88
     ответственности
    0.86
     pacote
    0.86
     গিয়ে
    0.86
    Act Density 0.004%

    No Known Activations