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

    Neuronpedia

    INDEX
    Explanations

    transcript

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     responsible
    -0.08
     responsável
    -0.08
    ivitis
    -0.08
     geste
    -0.08
     अच्छी
    -0.08
     batu
    -0.08
     Favorites
    -0.08
    举
    -0.08
    Responsible
    -0.08
     Saturn
    -0.08
    POSITIVE LOGITS
     transcripts
    0.14
     transcript
    0.13
     Transcript
    0.11
     Speech
    0.10
     speeches
    0.09
     hearings
    0.09
    録
    0.09
     speech
    0.09
    会议
    0.09
    Transcript
    0.09
    Act Density 0.017%

    No Known Activations