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

    Neuronpedia

    INDEX
    Explanations

    Exercise instructions and equipment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     turnkey
    -0.08
     экономики
    -0.08
     обслуживания
    -0.08
     Annual
    -0.07
     Econom
    -0.07
     оператив
    -0.07
     Economia
    -0.07
     payé
    -0.07
     December
    -0.07
     wholesale
    -0.07
    POSITIVE LOGITS
     modi
    0.09
     sitter
    0.08
    utron
    0.08
    ut
    0.08
     kişi
    0.08
    istically
    0.08
     hulpm
    0.08
    amba
    0.08
     <!--
    0.08
     �
    0.08
    Act Density 0.099%

    No Known Activations