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

    Neuronpedia

    INDEX
    Explanations

    die

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     die
    -1.02
     bien
    -0.75
     
    -0.72
     N
    -0.66
     beliefs
    -0.66
     di
    -0.65
     unlikely
    -0.64
     the
    -0.61
     Or
    -0.61
     Scha
    -0.61
    POSITIVE LOGITS
     Shakspeare
    1.02
     Monfieur
    1.01
     raiſ
    0.96
     itſelf
    0.95
     uſed
    0.93
     Diſ
    0.88
     Jefus
    0.88
     poffe
    0.86
     Houſe
    0.84
     ſy
    0.84
    Act Density 0.644%

    No Known Activations