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

    Neuronpedia

    INDEX
    Explanations

    per

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nakalista
    -0.74
    numerusform
    -0.68
     AspNetCore
    -0.68
    ItemBackground
    -0.67
     otomatig
    -0.66
    ConstraintMaker
    -0.63
    MemoryWarning
    -0.63
     Económica
    -0.61
     StatefulWidget
    -0.60
    MergeFrom
    -0.60
    POSITIVE LOGITS
     étro
    0.53
    line
    0.50
    long
    0.50
    ology
    0.49
    sz
    0.48
     alluminio
    0.47
    lines
    0.46
     échanti
    0.46
    opts
    0.45
    ďaka
    0.45
    Act Density 0.029%

    No Known Activations