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

    Neuronpedia

    INDEX
    Explanations

    Follow-up emails

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ഇവ
    -0.07
    Announcements
    -0.07
     did
    -0.07
    LEE
    -0.07
     THEN
    -0.07
     эх
    -0.07
    decl
    -0.07
     établissements
    -0.07
     sorties
    -0.07
    NAME
    -0.07
    POSITIVE LOGITS
    一下
    0.08
     bezüglich
    0.08
     maidir
    0.07
     bitte
    0.07
     Please
    0.07
     crossroads
    0.07
     Picks
    0.07
     لح
    0.07
     చేస్తున్న
    0.07
     tranquille
    0.07
    Act Density 0.008%

    No Known Activations