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

    Neuronpedia

    INDEX
    Explanations

    security and advantages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fakt
    0.80
    |");
    0.79
     perasaan
    0.74
     sentimos
    0.73
    ;');
    0.73
    🤬
    0.72
     બાળ
    0.71
    মন্ত
    0.71
    പ്പു
    0.70
     konkuren
    0.70
    POSITIVE LOGITS
    ＿
    0.73
    后
    0.71
    实体
    0.70
    캐
    0.70
    Під
    0.70
    旁边
    0.69
    lyk
    0.69
    底下
    0.67
    𝑪
    0.65
    يا
    0.65
    Act Density 0.000%

    No Known Activations