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

    Neuronpedia

    INDEX
    Explanations

    Lists and colons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     to
    -0.54
    ("")]
    -0.44
     esteja
    -0.44
     or
    -0.42
     Do
    -0.42
     To
    -0.41
    /
    -0.41
     trouve
    -0.40
     Just
    -0.39
     do
    -0.39
    POSITIVE LOGITS
     Efq
    0.98
     виправивши
    0.84
     Monfieur
    0.84
    IntoConstraints
    0.84
     Jefus
    0.82
     myſelf
    0.81
    aarrggbb
    0.79
    GEBURTSDATUM
    0.78
    WithIOException
    0.78
    StoryboardSegue
    0.78
    Act Density 0.003%

    No Known Activations