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

    Neuronpedia

    INDEX
    Explanations

    code breaks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Indoor
    -0.08
     Voj
    -0.07
    istr
    -0.06
     PPC
    -0.06
    گانی
    -0.06
    аны
    -0.06
    Pager
    -0.06
     Fab
    -0.06
    Messenger
    -0.06
    (coll
    -0.05
    POSITIVE LOGITS
     после
    0.06
     demonstrate
    0.06
     bd
    0.06
     Constructs
    0.06
    _Property
    0.06
    _ROT
    0.06
     dernier
    0.06
     mat
    0.06
     美国
    0.06
    lick
    0.06
    Act Density 0.012%

    No Known Activations