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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     COS
    -0.07
    ovny
    -0.07
     shipment
    -0.07
    defines
    -0.06
    Next
    -0.06
     kişi
    -0.06
     ne
    -0.06
    DRAW
    -0.06
    615
    -0.06
     вважа
    -0.06
    POSITIVE LOGITS
    _each
    0.06
     offic
    0.06
     Jonah
    0.06
    \Catalog
    0.06
    ):
↵
↵
    0.05
    stanov
    0.05
    领导
    0.05
     Lomb
    0.05
    _OscInitStruct
    0.05
     mitig
    0.05
    Act Density 0.085%

    No Known Activations