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

    Neuronpedia

    INDEX
    Explanations

    function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    intérêt
    0.40
    ésus
    0.40
    äs
    0.39
    ersham
    0.39
    írás
    0.39
    Lor
    0.39
     бясплат
    0.39
    ürlich
    0.38
    牷
    0.38
    enseit
    0.37
    POSITIVE LOGITS
     create
    0.47
     hello
    0.47
     kafka
    0.44
     get
    0.43
     json
    0.42
     greet
    0.41
     __
    0.39
     장
    0.39
     jsonify
    0.38
     registrar
    0.38
    Act Density 0.012%

    No Known Activations