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

    Neuronpedia

    INDEX
    Explanations

    Code/file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    delete
    -0.07
    (Float
    -0.07
     quantidade
    -0.06
     ***/↵
    -0.06
    _DX
    -0.06
    Ham
    -0.06
    	super
    -0.06
    .Engine
    -0.06
     Bundle
    -0.06
    latitude
    -0.06
    POSITIVE LOGITS
    oron
    0.07
     liners
    0.07
    .Diagnostics
    0.07
    Capability
    0.06
    における
    0.06
    ческой
    0.06
     Capability
    0.06
    utral
    0.06
    сторія
    0.06
    -‐
    0.06
    Act Density 0.011%

    No Known Activations