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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     subtraction
    -0.07
     RUS
    -0.06
     Reve
    -0.06
    Radians
    -0.06
    ToggleButton
    -0.06
    عود
    -0.06
     Che
    -0.06
     Raider
    -0.06
     ποι
    -0.06
     Ras
    -0.06
    POSITIVE LOGITS
     investing
    0.06
    <html
    0.06
    %D
    0.06
    precated
    0.06
     dealt
    0.06
    DDL
    0.06
    :new
    0.06
    tax
    0.06
     sollten
    0.06
    รง
    0.06
    Act Density 0.042%

    No Known Activations