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

    Neuronpedia

    INDEX
    Explanations

    wire cage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ̣t
    0.78
     애플
    0.78
    雰囲気
    0.78
     comptes
    0.74
     disponibili
    0.73
    ोबर
    0.73
    ாள்
    0.73
     حر
    0.72
    കളുടെ
    0.69
    คคล
    0.69
    POSITIVE LOGITS
    人
    0.92
    რე
    0.78
    ciendo
    0.78
     conceding
    0.77
    kita
    0.75
     milky
    0.74
    人之
    0.74
     walking
    0.74
     maintaining
    0.74
     DeL
    0.72
    Act Density 0.000%

    No Known Activations