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

    Neuronpedia

    INDEX
    Explanations

    thus hence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ths
    -0.08
     నేత
    -0.08
     potem
    -0.08
    THOOK
    -0.08
     تاسو
    -0.08
     Stad
    -0.08
    leda
    -0.08
    ქონ
    -0.07
    ですが
    -0.07
     നഗ
    -0.07
    POSITIVE LOGITS
     decidedly
    0.10
     reiter
    0.09
     restful
    0.08
     apt
    0.08
     I'll
    0.08
     прод
    0.08
     reaffirm
    0.08
     définitivement
    0.07
     again
    0.07
     crossroads
    0.07
    Act Density 0.102%

    No Known Activations