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

    Neuronpedia

    INDEX
    Explanations

    organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AsUp
    -0.95
     Diſ
    -0.85
     purpoſe
    -0.83
     Eſ
    -0.81
     Reſ
    -0.81
     iſt
    -0.80
     Monfieur
    -0.79
     Houſe
    -0.79
     feroit
    -0.76
     Jefus
    -0.76
    POSITIVE LOGITS
     of
    0.95
     for
    0.64
     Of
    0.62
     is
    0.54
    ’
    0.53
    Of
    0.52
     OF
    0.50
    '
    0.50
    ment
    0.50
    of
    0.49
    Act Density 0.075%

    No Known Activations