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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Echo
    -0.08
    Anh
    -0.07
     restful
    -0.07
     Harm
    -0.07
     dulu
    -0.07
    rown
    -0.07
    Distr
    -0.07
    Sun
    -0.07
    Distinct
    -0.07
    Sum
    -0.07
    POSITIVE LOGITS
    ுக்கள்
    0.09
    籍
    0.09
    boards
    0.09
    angles
    0.09
    ologies
    0.08
    ਨਾਂ
    0.08
     dá
    0.08
    ிகளில்
    0.08
    গুলো
    0.08
    ોમાં
    0.08
    Act Density 0.610%

    No Known Activations