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

    Neuronpedia

    INDEX
    Explanations

    past-tense verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     candidates
    -0.07
    udios
    -0.07
     teams
    -0.07
     Kont
    -0.07
     cohort
    -0.07
    Teams
    -0.07
    X
    -0.06
     donors
    -0.06
     asset
    -0.06
     Doc
    -0.06
    POSITIVE LOGITS
    _WATCH
    0.07
     millionaire
    0.07
    .navigationItem
    0.06
    еса
    0.06
    いや
    0.06
     воспал
    0.06
    уча
    0.06
     зн
    0.06
     значит
    0.06
     DISCLAIMER
    0.06
    Act Density 0.165%

    No Known Activations