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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.69
    IsPostBack
    -0.65
    +#+#
    -0.65
    esModule
    -0.63
    SBATCH
    -0.62
    IBOutlet
    -0.60
    ness
    -0.59
    bcrypt
    -0.55
    parsedMessage
    -0.54
     Vors
    -0.54
    POSITIVE LOGITS
     réfrig
    0.70
     présidenti
    0.61
    Française
    0.60
     refusé
    0.60
     heureuse
    0.59
     armées
    0.59
    edos
    0.59
     traités
    0.58
     condamné
    0.58
     vagyok
    0.57
    Act Density 0.087%

    No Known Activations