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

    Neuronpedia

    INDEX
    Explanations

    legal services

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    広
    -0.07
    579
    -0.07
    Preferences
    -0.07
    Camera
    -0.07
    diamond
    -0.07
    277
    -0.07
    겨
    -0.07
    tracted
    -0.07
    Intro
    -0.06
     corrosion
    -0.06
    POSITIVE LOGITS
    ,:),
    0.07
    ère
    0.07
     والد
    0.07
    .connected
    0.06
    .matcher
    0.06
     masc
    0.06
     (?)
    0.06
     exhilar
    0.06
    ?>/
    0.06
    ),$
    0.06
    Act Density 0.015%

    No Known Activations