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

    Neuronpedia

    INDEX
    Explanations

    log files and configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pas
    -0.07
     hazardous
    -0.07
    .ByteString
    -0.07
    은
    -0.07
    奔波
    -0.07
     Donna
    -0.06
    Women
    -0.06
     ולא
    -0.06
     Hơn
    -0.06
    .Step
    -0.06
    POSITIVE LOGITS
    layouts
    0.08
    כים
    0.08
     nak
    0.07
    spell
    0.07
     speculative
    0.07
    akra
    0.06
    skill
    0.06
    acles
    0.06
    UIKit
    0.06
     admirable
    0.06
    Act Density 0.025%

    No Known Activations