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

    Neuronpedia

    INDEX
    Explanations

    international

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .lon
    -0.07
    .LastName
    -0.06
    .acc
    -0.06
    krom
    -0.06
     durability
    -0.06
    .pan
    -0.06
     paramMap
    -0.06
     亚洲
    -0.06
    农业
    -0.06
    folder
    -0.06
    POSITIVE LOGITS
    ーボ
    0.08
     가장
    0.07
     tweak
    0.07
     Effective
    0.06
    ()):
    0.06
    ULL
    0.06
    алог
    0.06
     period
    0.06
     Flake
    0.06
    .Down
    0.06
    Act Density 0.002%

    No Known Activations