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

    Neuronpedia

    INDEX
    Explanations

    Sprite

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .hm
    -0.08
     Patterson
    -0.07
    metros
    -0.07
    _fid
    -0.07
     reperc
    -0.07
     margins
    -0.07
    .for
    -0.07
    (userId
    -0.07
    ortality
    -0.07
     IUser
    -0.06
    POSITIVE LOGITS
    wchar
    0.07
    女儿
    0.07
    тя
    0.07
    樹
    0.07
     NPC
    0.07
     stylish
    0.06
    氢
    0.06
     imaginative
    0.06
     emot
    0.06
     steering
    0.06
    Act Density 0.001%

    No Known Activations