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

    Neuronpedia

    INDEX
    Explanations

    equality operator

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Like
    -0.08
    loud
    -0.07
    间的
    -0.07
    了不少
    -0.07
     compr
    -0.07
     involve
    -0.07
     forward
    -0.07
    ([]);↵
    -0.07
     nose
    -0.06
     lots
    -0.06
    POSITIVE LOGITS
     dwóch
    0.08
     cosmetic
    0.08
    𝒊
    0.07
    カード
    0.07
    ┘
    0.07
     counselling
    0.07
    .chk
    0.07
    اي
    0.07
     mystical
    0.07
    珋
    0.07
    Act Density 0.041%

    No Known Activations