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

    Neuronpedia

    INDEX
    Explanations

    negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     பூ
    -0.09
     Coy
    -0.08
     déplacement
    -0.08
     deficiência
    -0.08
     прох
    -0.08
     kõik
    -0.07
     NS
    -0.07
    гал
    -0.07
    편
    -0.07
     гр
    -0.07
    POSITIVE LOGITS
     wirklich
    0.10
     necessarily
    0.09
    真正
    0.09
     إلا
    0.09
     priorit
    0.09
     adequately
    0.09
     vraiment
    0.09
     heller
    0.08
     tampoco
    0.08
     veramente
    0.08
    Act Density 0.033%

    No Known Activations