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

    Neuronpedia

    INDEX
    Explanations

    Chinese suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ifen
    -0.08
     STANDARD
    -0.07
    -sw
    -0.07
    _None
    -0.06
    yield
    -0.06
     bind
    -0.06
     damning
    -0.06
     FREE
    -0.06
     لك
    -0.06
     Exception
    -0.06
    POSITIVE LOGITS
    Rocket
    0.07
    Archivo
    0.07
    Від
    0.07
    つの
    0.07
    }*/↵
    0.07
    subcategory
    0.06
    Qi
    0.06
     sessiz
    0.06
     목소
    0.06
    OTA
    0.06
    Act Density 0.001%

    No Known Activations