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

    Neuronpedia

    INDEX
    Explanations

    bachelor's degree

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bladder
    -0.07
     mailbox
    -0.07
     spam
    -0.07
     Mur
    -0.07
     Gun
    -0.06
    Mur
    -0.06
    icts
    -0.06
    ников
    -0.06
    ��
    -0.06
     decipher
    -0.06
    POSITIVE LOGITS
    ATAL
    0.07
    atal
    0.06
    [jj
    0.06
    .Errors
    0.06
     mutlaka
    0.06
     BMP
    0.06
    NSSet
    0.06
     ราย
    0.06
     Jessica
    0.06
    cleanup
    0.06
    Act Density 0.013%

    No Known Activations