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

    Neuronpedia

    INDEX
    Explanations

    news articles and headlines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    1.16
     It
    1.05
      
    0.96
    In
    0.94
    What
    0.94
    ↵↵
    0.93
     In
    0.92
    <0x0D>
    0.92
    0.90
    It
    0.89
    POSITIVE LOGITS
    사
    1.18
    א
    0.92
     apie
    0.85
    ме
    0.85
    드
    0.85
     acerca
    0.83
    나
    0.83
    ない
    0.82
    ாய்
    0.81
    ア
    0.81
    Act Density 0.010%

    No Known Activations