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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    စ
    -0.07
     energía
    -0.07
    项
    -0.07
    .Audio
    -0.07
    ipo
    -0.07
    lbl
    -0.07
     develop
    -0.07
    野心
    -0.07
    謂
    -0.07
    dispatch
    -0.07
    POSITIVE LOGITS
    当地时间
    0.07
    忮
    0.07
    ?”↵↵
    0.06
    )],
    0.06
     determinant
    0.06
    🍗
    0.06
    荩
    0.06
     Nets
    0.06
    ]';↵
    0.06
    赋能
    0.06
    Act Density 0.029%

    No Known Activations