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

    Neuronpedia

    INDEX
    Explanations

    bundles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cent
    -1.02
    mate
    -0.77
     Cent
    -0.71
    s
    -0.68
    cent
    -0.66
    mates
    -0.63
    Cent
    -0.62
     deals
    -0.60
     agreements
    -0.59
     bundles
    -0.59
    POSITIVE LOGITS
     propOrder
    0.90
     للمعارف
    0.81
    ConstraintMaker
    0.79
    httphttps
    0.75
    IntoConstraints
    0.75
    LookAnd
    0.73
     jScrollPane
    0.73
     Normdatei
    0.73
    hdashline
    0.71
    twimg
    0.71
    Act Density 0.461%

    No Known Activations