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

    Neuronpedia

    INDEX
    Explanations

    Non

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _records
    -0.07
     проте
    -0.06
    HL
    -0.06
    ERC
    -0.06
     kå
    -0.06
    DOM
    -0.06
     languages
    -0.06
     pepper
    -0.06
     arrows
    -0.06
     definition
    -0.06
    POSITIVE LOGITS
     conforms
    0.07
     nhựa
    0.07
     sessiz
    0.07
    ConfigureAwait
    0.06
    omencl
    0.06
     конструкции
    0.06
     imagin
    0.06
    Constraint
    0.06
    tol
    0.06
     -->
↵
    0.06
    Act Density 0.003%

    No Known Activations