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

    Neuronpedia

    INDEX
    Explanations

    children

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     imitation
    -0.07
     thị
    -0.06
    alist
    -0.06
     sciences
    -0.06
    аем
    -0.06
    овал
    -0.06
    -domain
    -0.06
    ced
    -0.06
    oire
    -0.06
    Když
    -0.06
    POSITIVE LOGITS
     ew
    0.07
     storyt
    0.06
    owering
    0.06
     swapped
    0.06
     mozilla
    0.06
     år
    0.06
    (reply
    0.06
    (exit
    0.06
     �
    0.06
    ۱۶
    0.06
    Act Density 0.002%

    No Known Activations