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

    Neuronpedia

    INDEX
    Explanations

    numbers and statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dou
    -0.07
     Kad
    -0.07
    _os
    -0.06
    _report
    -0.06
    уры
    -0.06
    (Web
    -0.06
     Пок
    -0.06
     zůst
    -0.06
    AUTH
    -0.06
     uphill
    -0.06
    POSITIVE LOGITS
    inator
    0.07
    ninger
    0.06
     meas
    0.06
     Abdullah
    0.06
     tas
    0.06
    icio
    0.06
    ffb
    0.06
     rok
    0.06
    ленный
    0.06
    igeria
    0.06
    Act Density 0.156%

    No Known Activations