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

    Neuronpedia

    INDEX
    Explanations

    Bi

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ly
    -0.97
    pi
    -0.85
    bi
    -0.83
    mi
    -0.81
     pi
    -0.79
     Bi
    -0.69
     bi
    -0.67
    oni
    -0.67
     Pi
    -0.66
    Bi
    -0.57
    POSITIVE LOGITS
     Efq
    1.30
     Houſe
    1.20
     Jefus
    1.16
     itſelf
    1.16
     ſche
    1.15
     houſe
    1.15
     myſelf
    1.13
     Monfieur
    1.12
     themſelves
    1.10
     ſtate
    1.09
    Act Density 0.135%

    No Known Activations