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

    Neuronpedia

    INDEX
    Explanations

    units of measurement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    廳
    -0.07
    +'
    -0.07
     cạnh
    -0.07
    키
    -0.06
     shapes
    -0.06
     H�
    -0.06
    -fi
    -0.06
     Audience
    -0.06
    ネル
    -0.06
     Be
    -0.06
    POSITIVE LOGITS
     incompatible
    0.07
     compelling
    0.07
     �
    0.06
    =test
    0.06
    ейств
    0.06
     adaptation
    0.06
     startTime
    0.06
     kunne
    0.06
     presenting
    0.06
     contaminated
    0.06
    Act Density 0.031%

    No Known Activations