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

    Neuronpedia

    INDEX
    Explanations

    special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     selectors
    -0.07
     overhe
    -0.07
     Dickens
    -0.07
    hhh
    -0.06
    dd
    -0.06
    _REGION
    -0.06
     oversh
    -0.06
     Singleton
    -0.06
    ，他们
    -0.06
     prosper
    -0.06
    POSITIVE LOGITS
     未
    0.07
    uture
    0.07
     медицин
    0.06
    津
    0.06
    .graphics
    0.06
    codegen
    0.06
    istema
    0.06
    ="//
    0.06
     gerçekten
    0.06
    อก
    0.06
    Act Density 0.091%

    No Known Activations