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

    Neuronpedia

    INDEX
    Explanations

    books and articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     book
    -0.76
     “
    -0.57
     
    -0.54
     f
    -0.54
     articles
    -0.53
     on
    -0.52
     content
    -0.51
     service
    -0.51
    tre
    -0.51
     m
    -0.50
    POSITIVE LOGITS
    LookAnd
    1.27
     Jefus
    1.16
     myſelf
    1.13
    StructEnd
    1.05
     itſelf
    1.04
    abestanden
    1.02
     Efq
    1.00
     Theſe
    0.99
     purpoſe
    0.99
    клопе
    0.97
    Act Density 0.154%

    No Known Activations