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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     समीक्षक
    -0.73
     vệ
    -0.57
    ,:),
    -0.56
    
    -0.54
    mtrl
    -0.54
     Candidates
    -0.53
     BeautifulSoup
    -0.52
    archical
    -0.52
     unsuspecting
    -0.52
    asymp
    -0.51
    POSITIVE LOGITS
     ouvriers
    0.60
     prêtres
    0.59
    DockStyle
    0.53
    resave
    0.51
    gitto
    0.50
     travailleurs
    0.49
    ||}
    0.49
     stället
    0.47
    Alike
    0.46
    ADELPHIA
    0.45
    Act Density 0.004%

    No Known Activations