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

    Neuronpedia

    INDEX
    Explanations

    完整

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     documentaries
    -0.08
     Hollywood
    -0.08
     хол
    -0.08
     Fah
    -0.07
     concerts
    -0.07
    ാട
    -0.07
     Tr
    -0.07
    emonic
    -0.07
     finances
    -0.07
    يجة
    -0.07
    POSITIVE LOGITS
     indentation
    0.09
     transcription
    0.09
     transcript
    0.09
    章节
    0.08
     मस
    0.08
     Transcript
    0.08
     transcripts
    0.08
    _indent
    0.08
    分页
    0.08
    Transcript
    0.08
    Act Density 0.002%

    No Known Activations