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

    Neuronpedia

    INDEX
    Explanations

    he

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     پرداخت
    -0.07
     kadınlar
    -0.07
    _defaults
    -0.06
    す
    -0.06
    BI
    -0.06
    Exception
    -0.06
    emaakt
    -0.06
    .RequestMapping
    -0.06
     nuestra
    -0.06
     같습니다
    -0.06
    POSITIVE LOGITS
     cabel
    0.07
     cheerful
    0.07
    liste
    0.07
    علام
    0.06
    片
    0.06
    =event
    0.06
    BW
    0.06
    imesteps
    0.06
     selfie
    0.06
     Baron
    0.06
    Act Density 0.040%

    No Known Activations