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

    Neuronpedia

    INDEX
    Explanations

    java imports and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RELATIVA
    0.46
    aży
    0.44
    <unused336>
    0.43
    <unused2015>
    0.43
     स्वादिष्ट
    0.42
    <unused1875>
    0.42
    preliquidacion
    0.42
     टीकाकरण
    0.42
    ूटूथ
    0.42
    瓤
    0.42
    POSITIVE LOGITS
    .*;
    0.49
    .
    0.47
     import
    0.46
    *
    0.45
    .*
    0.44
    ↵↵
    0.42
    ’
    0.40
    -
    0.38
          
    0.38
     P
    0.38
    Act Density 0.028%

    No Known Activations