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

    Neuronpedia

    INDEX
    Explanations

    chatbot messages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nordic
    -0.07
     wys
    -0.07
     рек
    -0.07
     Metropolitana
    -0.07
     ત
    -0.07
    gyl
    -0.07
    ®
    -0.07
     RW
    -0.07
    Vod
    -0.07
     Hun
    -0.07
    POSITIVE LOGITS
    ुवा
    0.09
     होते
    0.08
    _counts
    0.07
     exactement
    0.07
     некотор
    0.07
    (inter
    0.07
    Ratings
    0.07
    inherits
    0.07
    त्ती
    0.07
     déf
    0.07
    Act Density 0.190%

    No Known Activations