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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kam
    -0.08
     Europé
    -0.07
     Tra
    -0.07
     Jeanne
    -0.07
     expér
    -0.07
    cut
    -0.07
     Lance
    -0.07
    (){
    -0.07
    ------------------------------------------------------------------------
    -0.07
     Paste
    -0.07
    POSITIVE LOGITS
    ើម្បី
    0.08
    児
    0.08
     Summit
    0.07
     thoirt
    0.07
     જીત
    0.07
    、それ
    0.07
     SZ
    0.07
     slotxo
    0.07
     toirt
    0.07
     ferr
    0.07
    Act Density 0.197%

    No Known Activations