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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.60
     was
    -0.52
     our
    -0.48
    was
    -0.44
    ibid
    -0.42
     WAS
    -0.41
     web
    -0.39
    bcryptjs
    -0.39
    gameserver
    -0.38
    Was
    -0.37
    POSITIVE LOGITS
    клопе
    0.71
     purpoſe
    0.70
     mosques
    0.67
     reaſon
    0.66
     pleaſure
    0.66
     fevere
    0.65
     ſtate
    0.65
     Jérusalem
    0.65
    jectures
    0.65
     Serbs
    0.65
    Act Density 0.010%

    No Known Activations