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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Exhaust
    -0.07
    .Restr
    -0.06
     jej
    -0.06
     viewed
    -0.06
     emerged
    -0.06
    .myapplication
    -0.06
     Rift
    -0.06
     Peggy
    -0.06
     Assume
    -0.06
     nehmen
    -0.06
    POSITIVE LOGITS
    abble
    0.07
     UserManager
    0.06
    	fs
    0.06
    -auth
    0.06
    �
    0.06
    (flags
    0.06
    ‌کننده
    0.06
    slice
    0.06
    Рµ
    0.06
    crc
    0.06
    Act Density 0.057%

    No Known Activations