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

    Neuronpedia

    INDEX
    Explanations

    place names and figures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shakspeare
    -1.20
     ſtate
    -1.12
     Efq
    -1.12
     Cæsar
    -1.11
     itſelf
    -1.07
     ſche
    -1.06
     Monfieur
    -1.06
     houſe
    -1.05
     bershka
    -1.02
     fevere
    -1.01
    POSITIVE LOGITS
     the
    0.84
     and
    0.79
     A
    0.74
     in
    0.73
     N
    0.72
     a
    0.71
     L
    0.70
     I
    0.70
     Le
    0.70
     St
    0.69
    Act Density 0.232%

    No Known Activations