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

    Neuronpedia

    INDEX
    Explanations

    explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ensors
    -0.08
     thermique
    -0.08
     ndi
    -0.08
     Dzięki
    -0.07
    ンズ
    -0.07
     concr
    -0.07
     негізгі
    -0.07
    نور
    -0.07
     tremendous
    -0.07
     төп
    -0.07
    POSITIVE LOGITS
     legít
    0.12
     occasional
    0.12
     legitimately
    0.11
     legitimate
    0.10
     harmless
    0.10
     benign
    0.10
     geleg
    0.10
    正常
    0.10
     Legit
    0.09
     tolerated
    0.09
    Act Density 0.135%

    No Known Activations