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

    Neuronpedia

    INDEX
    Explanations

    detectors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mocks
    -0.07
    -&
    -0.07
    出
    -0.07
    ।↵
    -0.07
     cạnh
    -0.07
    Stamped
    -0.07
    ा।↵
    -0.06
    Hex
    -0.06
    .vars
    -0.06
     Reuters
    -0.06
    POSITIVE LOGITS
    .ins
    0.07
     использов
    0.06
    كييف
    0.06
    一緒
    0.06
    谁
    0.06
     yapıyor
    0.06
     Liability
    0.06
    matter
    0.06
    (sel
    0.06
    Stream
    0.05
    Act Density 0.080%

    No Known Activations