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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    *
    0.99
    <h3>
    0.96
    Furthermore
    0.87
    <h2>
    0.85
    Anthrop
    0.81
    Ther
    0.79
    .*
    0.78
    <h4>
    0.77
    Soci
    0.76
    Religious
    0.76
    POSITIVE LOGITS
     /*
    0.99
     //
    0.78
     设置
    0.64
    }",
    0.64
    ;}
    0.62
    }");
    0.60
     std
    0.59
     }
    0.59
     $("#"
    0.59
     rowIndex
    0.58
    Act Density 0.266%

    No Known Activations