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

    Neuronpedia

    INDEX
    Explanations

    Emotions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pattern
    -0.07
     yields
    -0.07
    파일
    -0.07
     copper
    -0.06
     ثم
    -0.06
    /png
    -0.06
    -dist
    -0.06
    นคร
    -0.06
     enfants
    -0.06
     Jean
    -0.06
    POSITIVE LOGITS
     emoc
    0.10
     dealer
    0.07
    จ
    0.06
    感情
    0.06
    ạm
    0.06
    Miss
    0.06
     emo
    0.06
     Famous
    0.06
    .ylabel
    0.06
     Azure
    0.06
    Act Density 0.003%

    No Known Activations