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

    Neuronpedia

    INDEX
    Explanations

    Descriptive text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    compact
    -0.07
     Islamabad
    -0.06
     Guards
    -0.06
     ساله
    -0.06
    �
    -0.06
     pa
    -0.06
     История
    -0.06
    Actual
    -0.06
     deutschen
    -0.06
    我
    -0.06
    POSITIVE LOGITS
    ้จ
    0.07
    ?
    0.06
     dönem
    0.06
    ९
    0.06
    649
    0.06
     corporations
    0.06
     fh
    0.06
    мот
    0.06
     qualifiers
    0.06
     облад
    0.06
    Act Density 0.045%

    No Known Activations