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

    Neuronpedia

    INDEX
    Explanations

    /text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sy
    -0.07
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    -0.07
    _Entity
    -0.07
     ass
    -0.07
    getClass
    -0.07
     Mongolia
    -0.07
    Type
    -0.07
    쇼
    -0.07
     cram
    -0.06
     برنامج
    -0.06
    POSITIVE LOGITS
    waukee
    0.07
    𝆹
    0.07
    -blocking
    0.06
    europäische
    0.06
    라도
    0.06
     decisión
    0.06
     comfortable
    0.06
    �
    0.06
    villa
    0.06
    몇
    0.06
    Act Density 0.001%

    No Known Activations