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

    Neuronpedia

    INDEX
    Explanations

    ox

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     declares
    -0.07
     precis
    -0.07
    /*----------------------------------------------------------------------------
    -0.06
    倒在
    -0.06
    ‧
    -0.06
    ]+"
    -0.06
     town
    -0.06
     каждый
    -0.06
    Doug
    -0.06
     TestUtils
    -0.06
    POSITIVE LOGITS
    regex
    0.07
    erca
    0.07
    ዛ
    0.07
    inosaur
    0.07
    _within
    0.07
    -platform
    0.07
    .configure
    0.07
    ��
    0.06
    selected
    0.06
    ność
    0.06
    Act Density 0.006%

    No Known Activations