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

    Neuronpedia

    INDEX
    Explanations

    scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ]));
↵
    -0.07
     Vall
    -0.06
     版
    -0.06
     kus
    -0.06
     Think
    -0.06
    oday
    -0.06
     EINA
    -0.06
     mại
    -0.06
     개
    -0.06
     Prote
    -0.06
    POSITIVE LOGITS
     dynam
    0.07
    limits
    0.07
    deadline
    0.07
    BUFFER
    0.06
    chap
    0.06
     _{}
    0.06
    -powered
    0.06
     strokes
    0.06
    blers
    0.06
    _mac
    0.06
    Act Density 0.383%

    No Known Activations