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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wab
    -0.08
     locker
    -0.08
     utrolig
    -0.08
     incroyable
    -0.07
     increíble
    -0.07
    weren
    -0.07
     мастер
    -0.07
    하면서
    -0.07
     normalerweise
    -0.07
     sorta
    -0.07
    POSITIVE LOGITS
     equally
    0.09
     одинаков
    0.08
     imaginable
    0.08
     necessariamente
    0.08
    IMA
    0.08
    necessarily
    0.07
     necesariamente
    0.07
     heir
    0.07
     Lima
    0.07
     Sime
    0.07
    Act Density 0.039%

    No Known Activations