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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     swinger
    -0.06
    Media
    -0.06
    igid
    -0.06
    _buf
    -0.06
    stick
    -0.06
     wake
    -0.06
    convert
    -0.06
    Planet
    -0.06
     eye
    -0.06
     homeschool
    -0.06
    POSITIVE LOGITS
    UGINS
    0.07
    CAM
    0.06
    モ
    0.06
     мг
    0.06
    Av
    0.06
    Aj
    0.06
     leggings
    0.06
     quart
    0.06
    ΡΓ
    0.06
    407
    0.06
    Act Density 0.005%

    No Known Activations