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

    Neuronpedia

    INDEX
    Explanations

    place names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,
    -0.60
     z
    -0.55
    di
    -0.54
    z
    -0.53
     
    -0.52
    es
    -0.52
     (
    -0.51
    se
    -0.50
    i
    -0.49
    j
    -0.48
    POSITIVE LOGITS
     Houſe
    1.48
     myſelf
    1.45
     Monfieur
    1.45
     itſelf
    1.44
     Jefus
    1.42
     Majefty
    1.41
     themſelves
    1.36
     himſelf
    1.34
     Efq
    1.32
     becauſe
    1.28
    Act Density 0.030%

    No Known Activations