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

    Neuronpedia

    INDEX
    Explanations

    =s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dés
    -0.07
    센
    -0.07
    لق
    -0.06
     vatandaş
    -0.06
     qué
    -0.06
    README
    -0.06
     яким
    -0.06
     وس
    -0.06
    Translate
    -0.06
     odv
    -0.06
    POSITIVE LOGITS
    pb
    0.07
    spender
    0.07
     McDonald
    0.07
     tails
    0.06
     visibility
    0.06
    .dao
    0.06
     Publications
    0.06
     grub
    0.06
    []=$
    0.06
    .ec
    0.06
    Act Density 0.000%

    No Known Activations