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
     marty
    -0.07
     scriptures
    -0.06
     rua
    -0.06
    _locals
    -0.06
     hops
    -0.06
     čt
    -0.06
    	IN
    -0.06
    acher
    -0.06
     Shirley
    -0.06
    atl
    -0.06
    POSITIVE LOGITS
    iệng
    0.07
    -development
    0.07
    glass
    0.07
     disposal
    0.07
    止
    0.06
    姓名
    0.06
    -topic
    0.06
    /oct
    0.06
     时间
    0.06
    起こ
    0.06
    Act Density 0.002%

    No Known Activations