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

    Neuronpedia

    INDEX
    Explanations

    state

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     elt
    -0.08
     Tor
    -0.07
    Tor
    -0.07
     Link
    -0.07
    ileceğini
    -0.07
     puan
    -0.06
    Part
    -0.06
    .Schedule
    -0.06
     cellphone
    -0.06
     числі
    -0.06
    POSITIVE LOGITS
    dent
    0.07
     faut
    0.07
     bpy
    0.06
     lectures
    0.06
    music
    0.06
    ging
    0.06
     /*----------------------------------------------------------------
    0.06
     astronomical
    0.06
     ⌒
    0.06
     UICollectionView
    0.06
    Act Density 0.006%

    No Known Activations