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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trunk
    -0.07
    \"",
    -0.07
     mất
    -0.07
     berries
    -0.06
    ethyst
    -0.06
     उद
    -0.06
    ंडल
    -0.06
     자동차
    -0.06
     numOf
    -0.06
     module
    -0.06
    POSITIVE LOGITS
    framework
    0.07
     πρέπει
    0.07
    Miami
    0.07
    合作
    0.06
     fsm
    0.06
    よう
    0.06
    isí
    0.06
    ssi
    0.06
     uvědom
    0.06
    d
    0.06
    Act Density 0.001%

    No Known Activations