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

    Neuronpedia

    INDEX
    Explanations

    assistance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Control
    -0.07
     CONTROL
    -0.07
     sorrow
    -0.07
     cz
    -0.06
    ующ
    -0.06
     pathlib
    -0.06
    قام
    -0.06
     control
    -0.06
    	sb
    -0.06
     propio
    -0.05
    POSITIVE LOGITS
     GetUser
    0.07
    eton
    0.07
    μιλος
    0.07
     Injury
    0.07
     Ack
    0.07
     Absolute
    0.07
    (Key
    0.06
    *e
    0.06
     vấn
    0.06
    teş
    0.06
    Act Density 0.002%

    No Known Activations