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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    colour
    -0.07
     Romanian
    -0.07
    Ze
    -0.07
    Sing
    -0.07
    inctions
    -0.06
    _dep
    -0.06
     something
    -0.06
     lists
    -0.06
    something
    -0.06
    Venta
    -0.06
    POSITIVE LOGITS
     суду
    0.06
     rab
    0.06
     zem
    0.06
     귀
    0.06
    �
    0.06
     арти
    0.06
     результате
    0.06
    시
    0.06
    alarda
    0.06
    ::_('
    0.06
    Act Density 0.111%

    No Known Activations