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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    èĵ
    -0.29
    anders
    -0.25
     volont
    -0.25
    prit
    -0.24
    广éĺĶ
    -0.24
    é¢Ħè§ģ
    -0.24
     tamp
    -0.24
     transcripts
    -0.23
    Bearer
    -0.23
     picnic
    -0.23
    POSITIVE LOGITS
    èĢĮæĿ¥
    0.30
    ance
    0.29
     Lesson
    0.26
    çŃ¾ä¸ĭ
    0.26
    raw
    0.26
    -beta
    0.26
     RAW
    0.25
     play
    0.25
    ла
    0.25
    icity
    0.25
    Act Density 0.229%

    No Known Activations