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

    Neuronpedia

    INDEX
    Explanations

    Code/references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ूं
    -0.07
    щей
    -0.07
    ("(
    -0.07
     deren
    -0.06
    ajo
    -0.06
    _Act
    -0.06
    ="(
    -0.06
     Stations
    -0.06
    �
    -0.06
    _codec
    -0.06
    POSITIVE LOGITS
    ????
    0.06
     khả
    0.06
     fores
    0.06
     tyre
    0.06
    inta
    0.06
     wear
    0.06
    多少
    0.06
    (the
    0.06
     технолог
    0.06
    اقع
    0.05
    Act Density 0.000%

    No Known Activations