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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Be
    -1.42
     to
    -1.13
     (
    -1.07
     
    -1.04
     be
    -1.01
    ,
    -1.00
    .
    -0.98
     By
    -0.98
    y
    -0.97
     by
    -0.95
    POSITIVE LOGITS
     myſelf
    2.41
     itſelf
    2.27
     Efq
    2.11
     raiſ
    2.05
     Jefus
    2.02
     Anſ
    2.02
     Majefty
    2.02
     themſelves
    2.00
     Monfieur
    1.98
     purpoſe
    1.95
    Act Density 2.746%

    No Known Activations