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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Aux
    -0.08
    SQL
    -0.07
    Phys
    -0.07
     zoek
    -0.06
    ڤ
    -0.06
     Deutsch
    -0.06
     spokes
    -0.06
    .Brand
    -0.06
     ראש
    -0.06
    Menus
    -0.06
    POSITIVE LOGITS
    IBUTE
    0.07
    互利
    0.07
    .disable
    0.07
     totals
    0.07
     Samantha
    0.06
     التداول
    0.06
    /model
    0.06
    )]↵
    0.06
    ]}"↵
    0.06
    还可以
    0.06
    Act Density 0.022%

    No Known Activations