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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    short
    -0.08
    CHANNEL
    -0.07
    [d
    -0.07
     prospective
    -0.07
    /co
    -0.07
     airborne
    -0.06
    legal
    -0.06
    Hide
    -0.06
     Barbar
    -0.06
    75
    -0.06
    POSITIVE LOGITS
     us
    0.07
    ğimiz
    0.06
     it
    0.06
     forControlEvents
    0.06
    教学
    0.06
    Enjoy
    0.06
     istediğiniz
    0.06
    ですか
    0.06
    们
    0.06
    είται
    0.06
    Act Density 0.014%

    No Known Activations