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

    Neuronpedia

    INDEX
    Explanations

    Recipe or Reason

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rior
    -0.07
    龍
    -0.06
     起
    -0.06
    aned
    -0.06
     ssize
    -0.06
     /↵↵
    -0.06
     Offensive
    -0.06
    ocode
    -0.06
    실
    -0.06
    igg
    -0.06
    POSITIVE LOGITS
    =__
    0.07
     polluted
    0.06
    �
    0.06
     glyph
    0.06
     khuyến
    0.06
     indispensable
    0.06
     utiliz
    0.06
     masturbation
    0.06
     utilizado
    0.06
     Waiting
    0.06
    Act Density 0.033%

    No Known Activations