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

    Neuronpedia

    INDEX
    Explanations

    <<

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tag
    -0.07
    holding
    -0.06
     ihren
    -0.06
    _paid
    -0.06
    	an
    -0.06
    Produto
    -0.06
     Tumblr
    -0.06
     취
    -0.06
    -exec
    -0.06
    ]'
    -0.06
    POSITIVE LOGITS
     secretly
    0.07
     Winchester
    0.07
     races
    0.07
     �
    0.06
     �
    0.06
    (`↵
    0.06
    [".
    0.06
     WAR
    0.06
     news
    0.06
    ::
    0.06
    Act Density 0.000%

    No Known Activations