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

    Neuronpedia

    INDEX
    Explanations

    confirm understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    1.78
    ↵↵↵
    1.57
    ↵
    1.48
    <h3>
    1.42
    ↵↵↵↵↵
    1.30
    <start_of_image>
    1.26
    </h2>
    1.25
    <h2>
    1.24
    ↵↵↵↵↵↵↵↵↵↵↵
    1.24
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.23
    POSITIVE LOGITS
     These
    1.08
    .
    0.98
     There
    0.98
     This
    0.98
     พวก
    0.91
     They
    0.89
     Here
    0.85
    。「
    0.85
     있는데요
    0.85
     Öncelikle
    0.84
    Act Density 2.269%

    No Known Activations