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

    Neuronpedia

    INDEX
    Explanations

    cide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ly
    -0.70
     Jung
    -0.66
    lada
    -0.65
     Ly
    -0.63
     na
    -0.62
     por
    -0.60
     ne
    -0.59
     Banks
    -0.58
     bal
    -0.57
    Ly
    -0.57
    POSITIVE LOGITS
     pleaſure
    0.83
     itſelf
    0.81
     houſe
    0.78
     purpoſe
    0.78
     Monfieur
    0.77
     ſtate
    0.76
     Efq
    0.76
     ſeveral
    0.75
     Houſe
    0.74
     varandra
    0.73
    Act Density 0.233%

    No Known Activations