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

    Neuronpedia

    INDEX
    Explanations

    punctuation and common words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '''↵↵
    -0.07
     speaker
    -0.07
    obot
    -0.07
     BUTTON
    -0.07
     ‘
    -0.07
     magnet
    -0.07
     ring
    -0.06
    hra
    -0.06
     ;
↵
↵
    -0.06
     udp
    -0.06
    POSITIVE LOGITS
    เภ
    0.08
     cramped
    0.08
    taient
    0.07
     likeness
    0.07
     encuentra
    0.06
    天堂
    0.06
     Falls
    0.06
    (ROOT
    0.05
     Đà
    0.05
    tridges
    0.05
    Act Density 0.069%

    No Known Activations