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

    Neuronpedia

    INDEX
    Explanations

    Leaders/teachers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     }:
    -0.07
    -my
    -0.07
     учрежд
    -0.06
     binds
    -0.06
     收
    -0.06
    Recognition
    -0.06
    .escape
    -0.06
    .active
    -0.06
    yyvsp
    -0.06
    安装
    -0.06
    POSITIVE LOGITS
    ces
    0.06
    _question
    0.06
    mmo
    0.06
    .ToolStripItem
    0.06
    JsonValue
    0.06
     sqr
    0.06
     hơi
    0.06
    ��
    0.06
    回答
    0.06
    _totals
    0.06
    Act Density 0.055%

    No Known Activations