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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ylabel
    -0.07
     upright
    -0.07
    олн
    -0.07
     IDb
    -0.06
    ).</
    -0.06
     تغ
    -0.06
    Rich
    -0.06
     detection
    -0.06
     Launch
    -0.06
    losure
    -0.06
    POSITIVE LOGITS
     have
    0.08
     has
    0.07
    anta
    0.07
    ’ve
    0.07
    've
    0.07
     qemu
    0.06
     franc
    0.06
    earn
    0.06
    jsonwebtoken
    0.06
     数
    0.06
    Act Density 0.038%

    No Known Activations