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

    Neuronpedia

    INDEX
    Explanations

    watches or jokes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     watch
    -0.77
    etti
    -0.63
     fread
    -0.57
     ComVisible
    -0.55
     getArguments
    -0.55
     AppModule
    -0.54
     MessageBoxIcon
    -0.53
    etto
    -0.53
     joke
    -0.52
     punch
    -0.52
    POSITIVE LOGITS
    requireNonNull
    0.60
    addCriterion
    0.60
    rooms
    0.59
    0.58
    consulté
    0.54
     AssemblyCompany
    0.54
    mates
    0.53
     ModelExpression
    0.53
    Бележки
    0.53
    houses
    0.52
    Act Density 0.027%

    No Known Activations