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

    Neuronpedia

    INDEX
    Explanations

    medical treatment and diagnosis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inei
    0.50
    akkhati
    0.46
    áns
    0.46
     až
    0.45
    ieli
    0.44
     added
    0.43
     tied
    0.43
    ান্ডের
    0.43
     stricken
    0.43
    árd
    0.43
    POSITIVE LOGITS
    ال
    0.49
    ทาง
    0.49
    ون
    0.46
    Easing
    0.45
    を取得
    0.43
    可行
    0.43
    ص
    0.43
    判断
    0.42
    治疗
    0.42
     المصفوف
    0.42
    Act Density 0.001%

    No Known Activations