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

    Neuronpedia

    INDEX
    Explanations

    mole

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Unfortunately
    -0.08
    _SN
    -0.07
    自觉
    -0.07
    massage
    -0.07
     Fans
    -0.07
    典型的
    -0.07
    ront
    -0.07
    回首
    -0.07
     past
    -0.07
    ASK
    -0.07
    POSITIVE LOGITS
    滉
    0.09
    煟
    0.07
     männer
    0.07
    熨
    0.07
     minOccurs
    0.07
     arbe
    0.07
    桷
    0.07
    Enviar
    0.07
     gốc
    0.07
    .lastName
    0.07
    Act Density 0.004%

    No Known Activations