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

    Neuronpedia

    INDEX
    Explanations

    CONFIG

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hosts
    -0.07
    dyn
    -0.07
    (true
    -0.06
    �
    -0.06
    _datasets
    -0.06
     disag
    -0.06
    too
    -0.06
     struggled
    -0.06
    ḋ
    -0.06
     Köln
    -0.06
    POSITIVE LOGITS
    ⇚
    0.07
     thiệu
    0.07
    rompt
    0.07
    cal
    0.07
    lette
    0.07
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    0.07
     ;-)
    0.07
     eval
    0.07
     bizarre
    0.06
    気軽に
    0.06
    Act Density 0.007%

    No Known Activations