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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cartoons
    -0.07
    anners
    -0.07
     todd
    -0.07
     stretching
    -0.07
     Adelaide
    -0.06
     drinking
    -0.06
     Pais
    -0.06
    VG
    -0.06
    ptron
    -0.06
     dreadful
    -0.06
    POSITIVE LOGITS
     zeigt
    0.07
    .prev
    0.07
    (pub
    0.06
    metro
    0.06
    ισμού
    0.06
     مختلف
    0.06
    __)
    0.06
    _geo
    0.05
     мав
    0.05
    (date
    0.05
    Act Density 0.053%

    No Known Activations