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
    Knowing
    -0.07
     trochu
    -0.07
     inmates
    -0.07
    �
    -0.07
    陆
    -0.07
     infected
    -0.07
     المغرب
    -0.06
     خواب
    -0.06
     kültür
    -0.06
     họp
    -0.06
    POSITIVE LOGITS
     scri
    0.08
    Contours
    0.06
    LOCKS
    0.06
     ascertain
    0.06
     embodies
    0.06
     athe
    0.06
    _die
    0.06
     justified
    0.06
    mploy
    0.06
    bab
    0.06
    Act Density 0.000%

    No Known Activations