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

    Neuronpedia

    INDEX
    Explanations

    biographies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     const
    -0.56
    Kariera
    -0.50
    туга
    -0.48
     Lumpur
    -0.46
    UNUSED
    -0.45
    гато
    -0.44
     dem
    -0.44
     des
    -0.43
    tyg
    -0.42
     P
    -0.41
    POSITIVE LOGITS
    s
    1.14
    ی
    1.13
     myſelf
    1.11
     Monfieur
    1.11
     itſelf
    1.05
     Efq
    1.02
    ed
    0.97
     Houſe
    0.93
     iſt
    0.93
     themſelves
    0.91
    Act Density 0.105%

    No Known Activations