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

    Neuronpedia

    INDEX
    Explanations

    District

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ulton
    -0.06
    .limit
    -0.06
     tension
    -0.06
     subst
    -0.06
     pads
    -0.06
    вроп
    -0.06
    (Entity
    -0.06
     Vega
    -0.06
    há
    -0.06
     oven
    -0.05
    POSITIVE LOGITS
    工业
    0.07
    ्रदर
    0.07
    _ms
    0.07
     Ç
    0.06
     Offering
    0.06
    _TYPE
    0.06
    leine
    0.06
    -ip
    0.06
    .”↵↵↵↵
    0.06
    Ph
    0.06
    Act Density 0.001%

    No Known Activations