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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arrange
    -0.07
    ᡡ
    -0.06
    Right
    -0.06
    举起
    -0.06
    刎
    -0.06
     occurrences
    -0.06
    -thirds
    -0.06
    Ask
    -0.06
    זו
    -0.06
     summ
    -0.06
    POSITIVE LOGITS
    田园
    0.08
    /ref
    0.07
    _RECORD
    0.07
     ancest
    0.07
    萜
    0.07
    涟
    0.07
    锆
    0.07
    图画
    0.07
    DCALL
    0.07
     בג
    0.07
    Act Density 0.048%

    No Known Activations