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

    Neuronpedia

    INDEX
    Explanations

    places or geographical context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     препратки
    -0.94
     Shakspeare
    -0.85
     myſelf
    -0.84
     greateſt
    -0.83
     uſed
    -0.81
     purpoſe
    -0.80
     Monfieur
    -0.79
     Houſe
    -0.77
     Diſ
    -0.77
     ainfi
    -0.76
    POSITIVE LOGITS
     river
    0.52
     dog
    0.52
     R
    0.51
     pr
    0.50
     w
    0.49
     my
    0.49
     ber
    0.49
     j
    0.48
     mor
    0.48
     li
    0.48
    Act Density 0.169%

    No Known Activations