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

    Neuronpedia

    INDEX
    Explanations

    negative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     voilà
    -0.09
     excellent
    -0.09
     attest
    -0.09
     dë
    -0.09
    সহ
    -0.08
    当然
    -0.08
     certainly
    -0.08
    આત
    -0.08
    Ваш
    -0.08
    itsa
    -0.08
    POSITIVE LOGITS
    遗漏
    0.11
     lurking
    0.10
     misunderstanding
    0.09
     overlooked
    0.09
     misunderstood
    0.09
     misunderstand
    0.09
     obscure
    0.09
     mistakes
    0.08
     undue
    0.08
     algún
    0.08
    Act Density 0.050%

    No Known Activations