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
     infatti
    -0.09
     indeed
    -0.08
     zwar
    -0.07
     inderdaad
    -0.07
     ಮತ್ತ
    -0.07
     bukan
    -0.07
     সত
    -0.07
    ieg
    -0.07
     değil
    -0.07
    λεί
    -0.07
    POSITIVE LOGITS
     మాత్రం
    0.16
    却
    0.10
     necesariamente
    0.09
    දි
    0.09
     අ
    0.08
     necessariamente
    0.08
     دو
    0.08
     overall
    0.08
     SYS
    0.08
     අව
    0.08
    Act Density 0.191%

    No Known Activations