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

    Neuronpedia

    INDEX
    Explanations

    types of things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.76
    modelBuilder
    -0.70
     HasFactory
    -0.68
    -0.65
     houſe
    -0.62
     Cæsar
    -0.60
     myſelf
    -0.60
     faſt
    -0.60
    MigrationBuilder
    -0.59
     becauſe
    -0.59
    POSITIVE LOGITS
     autorytatywna
    0.60
    ffine
    0.54
    出版年
    0.53
     تانيه
    0.52
    lapsingToolbar
    0.52
    żeli
    0.50
    bitField
    0.50
    Autoritní
    0.50
     دیکھیے
    0.49
    достатки
    0.48
    Act Density 1.522%

    No Known Activations