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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     भगव
    -0.05
     blo
    -0.05
     představ
    -0.05
     infants
    -0.05
    .Add
    -0.05
    .writerow
    -0.05
    　　　　　 　
    -0.05
     preservation
    -0.05
    _hash
    -0.05
     dünya
    -0.05
    POSITIVE LOGITS
    Ghost
    0.07
     높
    0.07
    opher
    0.07
     trigger
    0.07
    !!!
    0.06
    iosk
    0.06
    /channel
    0.06
    =./
    0.06
     امروز
    0.06
     desc
    0.06
    Act Density 0.014%

    No Known Activations