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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vy
    -0.07
    анк
    -0.07
    _blk
    -0.06
    clado
    -0.06
    _xml
    -0.06
    -Man
    -0.06
     virt
    -0.06
     Bone
    -0.06
    }],
    -0.06
    дем
    -0.06
    POSITIVE LOGITS
    ":↵↵
    0.06
    :↵↵
    0.06
    時
    0.06
     Breast
    0.06
    ：↵↵
    0.06
    .sessions
    0.06
     :↵
    0.06
     фин
    0.06
    <count
    0.06
     общ
    0.06
    Act Density 0.021%

    No Known Activations