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

    Neuronpedia

    INDEX
    Explanations

    Buenas tardes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ）」
    0.38
     eyelashes
    0.36
     plabic
    0.36
    ignés
    0.35
    __*/
    0.34
    就要
    0.33
    憸
    0.33
    廛
    0.33
     reinforcing
    0.32
    >`;
    0.32
    POSITIVE LOGITS
    <h2>
    0.96
    <table>
    0.88
    <h3>
    0.54
    Normdaten
    0.54
    |}
    0.46
    ↵↵↵↵↵
    0.45
      
    0.45
     Commons
    0.45
    *
    0.45
    <h4>
    0.40
    Act Density 0.000%

    No Known Activations