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

    Neuronpedia

    INDEX
    Explanations

    common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Dis
    -0.07
    .room
    -0.06
    _De
    -0.06
     uniqu
    -0.06
    TypeError
    -0.06
    forc
    -0.06
     cytok
    -0.06
    _SN
    -0.06
    GLOSS
    -0.06
    internet
    -0.06
    POSITIVE LOGITS
     chúng
    0.08
     yeri
    0.07
     Kernel
    0.07
    	ext
    0.06
    reich
    0.06
    स
    0.06
    845
    0.06
     impairment
    0.06
    松
    0.06
     Awesome
    0.06
    Act Density 0.055%

    No Known Activations