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

    Neuronpedia

    INDEX
    Explanations

    music

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Drawing
    -0.07
     Doug
    -0.06
     McK
    -0.06
     Bread
    -0.06
     Markt
    -0.06
    izontal
    -0.06
    _PADDING
    -0.06
    اشی
    -0.06
    777
    -0.06
     Path
    -0.06
    POSITIVE LOGITS
    包括
    0.07
    trieve
    0.07
     exploiting
    0.07
     laten
    0.07
    _generation
    0.07
     bulunmaktadır
    0.07
     servo
    0.06
     linea
    0.06
     були
    0.06
     singer
    0.06
    Act Density 0.091%

    No Known Activations