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

    Neuronpedia

    INDEX
    Explanations

    adverbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    再
    -0.06
    ]]:↵
    -0.06
     if
    -0.06
     сел
    -0.06
    ;i
    -0.06
     chapters
    -0.06
    _decimal
    -0.06
     д
    -0.06
     UPDATED
    -0.06
     For
    -0.06
    POSITIVE LOGITS
    _DEAD
    0.08
    ento
    0.07
    *sp
    0.07
    elay
    0.06
    不好
    0.06
    　　 　 　 　 　
    0.06
    INTER
    0.06
    walker
    0.06
    wayne
    0.06
    istrov
    0.06
    Act Density 0.148%

    No Known Activations