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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     打
    -0.07
    Eight
    -0.07
     algún
    -0.06
     bằng
    -0.06
     juga
    -0.06
     götür
    -0.06
     равно
    -0.06
    。不过
    -0.06
    ------↵↵
    -0.06
     espionage
    -0.06
    POSITIVE LOGITS
    ashed
    0.07
    im
    0.06
    シ
    0.06
    يدي
    0.06
     MOUSE
    0.06
    ジョ
    0.06
    (DE
    0.06
     garn
    0.06
    .comments
    0.06
     imply
    0.06
    Act Density 0.034%

    No Known Activations