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

    Neuronpedia

    INDEX
    Explanations

    circular

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clinging
    -0.08
     outdoors
    -0.07
     Jerseys
    -0.07
     toughness
    -0.07
    フランス
    -0.07
    License
    -0.07
    surface
    -0.07
    ﾈ
    -0.07
     Furniture
    -0.06
     furnished
    -0.06
    POSITIVE LOGITS
    ola
    0.07
    ются
    0.07
    Phil
    0.06
    欧阳
    0.06
    ᗷ
    0.06
    dos
    0.06
    猪
    0.06
     Hint
    0.06
    лев
    0.06
    ϰ
    0.06
    Act Density 0.004%

    No Known Activations