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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PEM
    -0.07
     Hurricanes
    -0.07
    笔试
    -0.07
    education
    -0.06
     documenting
    -0.06
    ighbors
    -0.06
    _devices
    -0.06
     Tutor
    -0.06
    .cloud
    -0.06
    关键技术
    -0.06
    POSITIVE LOGITS
     wyjątk
    0.07
    yellow
    0.07
     zwarte
    0.07
    _ROT
    0.07
     Giấy
    0.07
    سرط
    0.07
     tín
    0.06
    	D
    0.06
    黟
    0.06
     sluts
    0.06
    Act Density 0.109%

    No Known Activations