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

    Neuronpedia

    INDEX
    Explanations

    that/which (foreign languages)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     வார
    -0.08
    acters
    -0.08
     mare
    -0.07
    abe
    -0.07
     Cunningham
    -0.07
    Kaz
    -0.07
     envy
    -0.07
     Bale
    -0.07
     क्यों
    -0.07
    -0.07
    POSITIVE LOGITS
     ves
    0.09
    เกิด
    0.09
     buscas
    0.08
     تو
    0.08
     تع
    0.08
     اب
    0.08
    握
    0.08
    แ
    0.08
    �
    0.08
     determine
    0.08
    Act Density 0.056%
    No Known Activations