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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mail
    -0.06
    번호
    -0.06
     promising
    -0.06
    办公
    -0.06
     друг
    -0.06
    -provider
    -0.06
     keynote
    -0.06
     intimidating
    -0.06
    文章
    -0.05
    男人
    -0.05
    POSITIVE LOGITS
     Nhà
    0.06
     Meghan
    0.06
    Esta
    0.06
     Brendan
    0.06
    Requires
    0.06
     theolog
    0.06
     bevor
    0.06
    __(↵
    0.06
    @n
    0.06
    คอม
    0.06
    Act Density 0.492%

    No Known Activations