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

    Neuronpedia

    INDEX
    Explanations

    Code and layout

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     involuntary
    -0.07
    _folders
    -0.07
     robots
    -0.06
     Dillon
    -0.06
    万円
    -0.06
     payment
    -0.06
     Means
    -0.06
    -service
    -0.06
     '../../
    -0.06
     tỉnh
    -0.06
    POSITIVE LOGITS
     repl
    0.08
     Wow
    0.07
    athom
    0.07
    BB
    0.06
     swims
    0.06
     잡
    0.06
    itational
    0.06
    тивного
    0.06
     Ripple
    0.06
    CLICK
    0.06
    Act Density 0.021%

    No Known Activations