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

    Neuronpedia

    INDEX
    Explanations

    86

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (pDX
    -0.07
     standings
    -0.07
    vä
    -0.07
    ListComponent
    -0.06
    =query
    -0.06
    THON
    -0.06
    elope
    -0.06
     Rig
    -0.06
    파트
    -0.06
    INCLUDED
    -0.06
    POSITIVE LOGITS
    -na
    0.07
     dalla
    0.07
    २
    0.07
     AUX
    0.06
     emitted
    0.06
                              ↵
    0.06
     masked
    0.06
    ”的
    0.06
    imli
    0.06
     pena
    0.06
    Act Density 0.001%

    No Known Activations