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

    Neuronpedia

    INDEX
    Explanations

    renewed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Quote
    -0.07
    opi
    -0.07
     "&
    -0.07
     undeniable
    -0.07
    .time
    -0.06
    にする
    -0.06
    allis
    -0.06
     Times
    -0.06
    —all
    -0.06
     allerg
    -0.06
    POSITIVE LOGITS
    UGH
    0.07
    дии
    0.06
    )*/↵
    0.06
    ));↵↵↵
    0.06
    ैर
    0.06
    FormattedMessage
    0.06
    })↵↵↵
    0.06
    ec
    0.06
    刚才
    0.06
    esh
    0.06
    Act Density 0.000%

    No Known Activations