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

    Neuronpedia

    INDEX
    Explanations

    running

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    अप
    -0.08
    .).↵↵
    -0.08
    (column
    -0.08
     deline
    -0.07
    Europa
    -0.07
    (col
    -0.07
     проблем
    -0.07
    અ
    -0.07
    (term
    -0.07
    .PORT
    -0.07
    POSITIVE LOGITS
     계속
    0.09
     inmediatamente
    0.08
     조금
    0.08
    ictive
    0.08
     weiterhin
    0.08
     Fif
    0.08
     ચાલુ
    0.08
     없이
    0.08
     immédiatement
    0.07
     �
    0.07
    Act Density 0.006%

    No Known Activations