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

    Neuronpedia

    INDEX
    Explanations

    dr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Seymour
    -0.07
     �
    -0.07
     nya
    -0.06
     concussion
    -0.06
     Zoom
    -0.06
     [&](
    -0.06
    .attrs
    -0.06
    ınıf
    -0.06
    젠
    -0.06
    _PREF
    -0.06
    POSITIVE LOGITS
    dr
    0.08
    态
    0.08
     IDF
    0.08
    rase
    0.07
    под
    0.07
    der
    0.07
    streams
    0.06
    ám
    0.06
     دری
    0.06
    heard
    0.06
    Act Density 0.008%

    No Known Activations