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

    Neuronpedia

    INDEX
    Explanations

    academic papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (timeout
    -0.07
    ymmetric
    -0.06
     anticipating
    -0.06
     eldest
    -0.06
    ultz
    -0.06
    ymm
    -0.06
     parser
    -0.06
    oster
    -0.06
     attends
    -0.06
    огда
    -0.06
    POSITIVE LOGITS
     화
    0.07
    ROUGH
    0.07
     rocky
    0.07
    یه
    0.07
    -aut
    0.07
     بـ
    0.07
     ❤
    0.06
     LIMIT
    0.06
    /loose
    0.06
     HARD
    0.06
    Act Density 0.016%

    No Known Activations