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

    Neuronpedia

    INDEX
    Explanations

    /config

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Stretch
    -0.07
    ---
    -0.06
    Thumb
    -0.06
     año
    -0.06
    wall
    -0.06
    ovní
    -0.06
     todo
    -0.06
    -zero
    -0.06
     центр
    -0.06
    野
    -0.06
    POSITIVE LOGITS
     hdf
    0.07
     pokud
    0.07
    )';↵
    0.07
     Backpack
    0.07
    ='\
    0.07
    (",",
    0.06
    (strings
    0.06
    ')"↵
    0.06
     Blogger
    0.06
     backpack
    0.06
    Act Density 0.000%

    No Known Activations