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

    Neuronpedia

    INDEX
    Explanations

    Category

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    液
    -0.08
    盐
    -0.07
     kunne
    -0.07
    楒
    -0.07
     Gum
    -0.06
     certains
    -0.06
    'It
    -0.06
    违
    -0.06
     Regiment
    -0.06
     tract
    -0.06
    POSITIVE LOGITS
    .hover
    0.08
     Hướng
    0.08
     swo
    0.08
    6
    0.08
    endance
    0.07
    .preferences
    0.07
    (prob
    0.07
    と思っている
    0.07
    לצה
    0.07
    ogy
    0.07
    Act Density 0.021%

    No Known Activations