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

    Neuronpedia

    INDEX
    Explanations

    computer code and legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Datuak
    -0.53
    IntoConstraints
    -0.46
     Lap
    -0.44
    ThroughAttribute
    -0.43
    Hentet
    -0.43
     cu
    -0.43
    ioutil
    -0.42
    ConstraintMaker
    -0.42
    صه
    -0.41
    aktur
    -0.41
    POSITIVE LOGITS
     myſelf
    0.86
     itſelf
    0.82
     Monfieur
    0.79
     ſtate
    0.78
     Majefty
    0.77
     Jefus
    0.77
     himſelf
    0.75
     againſt
    0.73
     themſelves
    0.72
     purpoſe
    0.72
    Act Density 0.581%

    No Known Activations