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

    Neuronpedia

    INDEX
    Explanations

    prime

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prime
    -0.75
     premium
    -0.70
     Premium
    -0.63
    iting
    -0.61
     potential
    -0.58
    premium
    -0.58
    iding
    -0.57
    Premium
    -0.54
     ages
    -0.54
     minimal
    -0.52
    POSITIVE LOGITS
    MigrationBuilder
    0.98
    ConstraintMaker
    0.93
     AssemblyCompany
    0.79
     дописавши
    0.79
     CascadeType
    0.79
    LookAnd
    0.75
    resave
    0.75
    帖最后由
    0.73
    NewUrlParser
    0.73
    SequentialGroup
    0.71
    Act Density 0.134%

    No Known Activations