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
    ��
    -0.07
     witnessing
    -0.07
    -known
    -0.07
     duplicates
    -0.07
    .ค
    -0.06
     �
    -0.06
     tuples
    -0.06
     nghe
    -0.06
     customizable
    -0.06
    uchos
    -0.06
    POSITIVE LOGITS
    !")↵↵
    0.07
    　 　 　
    0.07
    ">*</
    0.06
    .CodeAnalysis
    0.06
    况
    0.06
    　 　 　 　
    0.06
     três
    0.06
     fanatic
    0.05
    dateTime
    0.05
    　 　 　 　 　
    0.05
    Act Density 0.087%

    No Known Activations