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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oin
    -0.07
    ry
    -0.07
    ่ง
    -0.07
    เร
    -0.06
    ayload
    -0.06
    PostalCodesNL
    -0.06
    ولة
    -0.06
    reds
    -0.06
    俺
    -0.06
    orea
    -0.06
    POSITIVE LOGITS
    .',
    0.07
     sc
    0.07
    萬
    0.06
    !important
    0.06
    >',
    0.06
    OptionPane
    0.06
    刺
    0.06
    =c
    0.06
    <!
    0.06
    γει
    0.06
    Act Density 0.003%

    No Known Activations