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

    Neuronpedia

    INDEX
    Explanations

    gradient

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ín
    -0.08
    ết
    -0.07
    arsed
    -0.07
    /env
    -0.07
     authToken
    -0.07
     EXAMPLE
    -0.06
     BRAND
    -0.06
    اگ
    -0.06
     trabajo
    -0.06
    ーテ
    -0.06
    POSITIVE LOGITS
     همچ
    0.07
     Cri
    0.06
    	RuntimeObject
    0.06
    .life
    0.06
    ++++++++++++++++
    0.06
    대회
    0.06
     porad
    0.06
    .Head
    0.06
    TypeID
    0.06
    Amy
    0.06
    Act Density 0.009%

    No Known Activations