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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fühl
    -0.07
     Cha
    -0.07
    これは
    -0.06
     combos
    -0.06
     lista
    -0.06
    苉
    -0.06
    얏
    -0.06
    ಊ
    -0.06
    说出
    -0.06
     Pokémon
    -0.06
    POSITIVE LOGITS
    incl
    0.07
    _CAL
    0.07
    inst
    0.07
    (in
    0.07
     FL
    0.07
     Residents
    0.07
    .extern
    0.07
     bulunmaktadır
    0.07
    漈
    0.07
    宝贵
    0.07
    Act Density 0.016%

    No Known Activations