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

    Neuronpedia

    INDEX
    Explanations

    ajax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     global
    -0.07
     První
    -0.07
     nowhere
    -0.07
     forefront
    -0.07
     préc
    -0.07
     Arbeit
    -0.07
     intf
    -0.07
    的に
    -0.06
     hostile
    -0.06
     UA
    -0.06
    POSITIVE LOGITS
     entertained
    0.08
     arising
    0.06
    Elizabeth
    0.06
    DbContext
    0.06
     ela
    0.06
    ğinde
    0.06
    <Any
    0.05
     lodging
    0.05
    promotion
    0.05
     жовтня
    0.05
    Act Density 0.015%

    No Known Activations