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

    Neuronpedia

    INDEX
    Explanations

    explaining things, indicating mood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused476>
    0.83
    প্রধান
    0.79
    ทุกคน
    0.76
    정책
    0.69
    MISS
    0.69
    <unused446>
    0.66
    Mira
    0.66
    \">
    0.65
    README
    0.64
    <unused2112>
    0.63
    POSITIVE LOGITS
    <0xE3>
    1.23
     অনুয
    1.15
     ()=>
    1.12
     নির্মান
    1.11
     बच्चो
    1.06
      
    1.06
     delà
    1.05
     लोगो
    1.04
     。
    0.99
    旳
    0.99
    Act Density 2.526%

    No Known Activations